© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44364
    Prev
    Next
    INDEX
    Explanations

    year / date context

    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
    泚
    -2.86
    🫅
    -2.69
    ⢕
    -2.66
    錞
    -2.58
     hebben
    -2.53
    嵎
    -2.53
    
    -2.48
     และ
    -2.48
    矬
    -2.48
    があります
    -2.45
    POSITIVE LOGITS
    The
    3.31
    h
    3.13
    le
    3.06
    You
    3.02
    3
    2.95
     Their
    2.92
    It
    2.86
    We
    2.78
    ve
    2.70
    多
    2.66
    Activations Density 0.095%

    No Known Activations