© 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. 99784
    Prev
    Next
    INDEX
    Explanations

    code imports or script beginnings

    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
     preocupa
    -1.95
     iniciativas
    -1.90
     ponen
    -1.75
     dunklen
    -1.74
     hilft
    -1.71
     decide
    -1.70
     encuentra
    -1.66
     recupera
    -1.66
     fortale
    -1.64
     れる
    -1.64
    POSITIVE LOGITS
    踅
    1.91
    <bos>
    1.82
    ஂ
    1.79
    齜
    1.77
    .
    1.67
    mayın
    1.65
     dorp
    1.63
     لأنه
    1.63
    <em>
    1.62
    They
    1.62
    Activations Density 0.001%

    No Known Activations