© 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. 22-GEMMASCOPE-RES-131K
    7. 67828
    Prev
    Next
    INDEX
    Explanations

    movies, films, and series

    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_22/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
     affrontare
    -1.04
    amble
    -1.00
     ￥
    -0.97
     замети
    -0.96
     maint
    -0.96
    ここは
    -0.94
    Passo
    -0.93
     tuturor
    -0.93
    Ҝ
    -0.92
    otum
    -0.92
    POSITIVE LOGITS
     movie
    1.20
     fictional
    1.16
    tagonist
    1.01
     portray
    0.98
    ₿
    0.96
     fic
    0.94
     of
    0.93
    リフォーム
    0.92
     film
    0.91
    映画
    0.88
    Activations Density 0.096%

    No Known Activations