© 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. 13828
    Prev
    Next
    INDEX
    Explanations

    committee

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ismet
    -1.73
     technologically
    -1.72
    ’
    -1.70
    各種
    -1.69
     amount
    -1.69
     entire
    -1.63
     opportunity
    -1.62
    牟
    -1.62
    といった
    -1.61
     kind
    -1.60
    POSITIVE LOGITS
    om
    2.28
    the
    2.28
    犰
    2.20
    肏
    2.20
    ting
    2.11
     Paesi
    2.09
    </sub>
    2.08
    $)$
    2.06
    al
    2.00
    なんとか
    1.94
    Activations Density 0.015%

    No Known Activations