© 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. 8743
    Prev
    Next
    INDEX
    Explanations

    Def prefix followed by word

    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
    所有人都
    -2.83
     „
    -2.47
     first
    -2.41
    唿
    -2.39
     неболь
    -2.36
    啻
    -2.36
     verwende
    -2.25
     dari
    -2.23
     escase
    -2.22
    
    -2.20
    POSITIVE LOGITS
    0
    3.03
    ’
    2.88
    ጪ
    2.63
    フライパン
    2.39
    目前
    2.39
    为什么
    2.33
    新しい
    2.31
    ～～～～
    2.31
    　“
    2.30
    ３
    2.28
    Activations Density 0.012%

    No Known Activations