© 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. 58769
    Prev
    Next
    INDEX
    Explanations

    DB table conversion

    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
    改装
    -2.53
     It
    -2.38
    同伴
    -2.33
     Of
    -2.33
    攫
    -2.30
    褥
    -2.23
    
    -2.22
    著名
    -2.20
    ⎔
    -2.20
    actéristi
    -2.19
    POSITIVE LOGITS
    捽
    2.53
    亖
    2.53
     tif
    2.30
    鈇
    2.30
    脑子
    2.28
    涷
    2.09
     sio
    2.09
    敺
    2.08
    
    2.06
    2
    2.03
    Activations Density 0.000%

    No Known Activations