© 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. 12356
    Prev
    Next
    INDEX
    Explanations

    actin and transcription

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

    biological terms, particularly proteins like actin, and words related to scientific transcription or gene expression.

    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
    ка
    -3.13
    ※※
    -2.72
    us
    -2.53
    2
    -2.42
    —“
    -2.42
    8
    -2.39
    er
    -2.38
    ————————————————
    -2.36
    There
    -2.33
    ◆◆
    -2.33
    POSITIVE LOGITS
    i
    2.88
    韡
    2.56
    ⢅
    2.53
    辄
    2.45
    謇
    2.45
    uatan
    2.44
    汭
    2.44
    </em>
    2.39
    すすめ
    2.36
     temporadas
    2.34
    Activations Density 0.020%

    No Known Activations