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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103839
    Prev
    Next
    INDEX
    Explanations

    L-segment or gene identifiers

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

    numerical designations, particularly numbers that follow letters in model numbers, scientific notations, or technical specifications.

    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
     Except
    -2.61
    Typically
    -2.44
     Unless
    -2.33
     Regardless
    -2.30
    Although
    -2.28
    茘
    -2.27
     Importantly
    -2.23
     Notwithstanding
    -2.22
    玧
    -2.19
    In
    -2.16
    POSITIVE LOGITS
    ]
    3.23
    ?"
    2.75
    ='
    2.72
    暃
    2.61
    也会
    2.45
    鷥
    2.45
    ſſel
    2.34
    \
    2.31
     adorned
    2.30
    ...."
    2.27
    Activations Density 0.033%

    No Known Activations