© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10049
    Prev
    Next
    INDEX
    Explanations

    ras and gene transfection

    np_acts-logits-general · gemini-2.5-flash-lite

    names of genes and proteins, particularly those containing "ras" and "onco" prefixes.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    gene-related terms like "ras" and "oncogene" in scientific literature.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    gene names and oncology-related protein terms (particularly "ras" and variations of oncogene).

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    genes and proteins associated with cancer research, particularly "ras" oncogenes.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -1.31
    ۱۶
    -1.25
    诟
    -1.23
    ۱۸
    -1.20
     pectoral
    -1.20
    我了
    -1.17
    ilige
    -1.17
     兩
    -1.16
    kapet
    -1.16
    網站
    -1.16
    POSITIVE LOGITS
     that
    1.74
     who
    1.57
     your
    1.40
    φαλ
    1.38
     again
    1.33
     our
    1.31
     those
    1.31
    𝕨
    1.29
    \_
    1.25
     the
    1.22
    Activations Density 0.179%

    No Known Activations