© 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. 105712
    Prev
    Next
    INDEX
    Explanations

    foreign words and food

    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
     them
    -1.91
     and
    -1.82
     who
    -1.75
     should
    -1.65
     with
    -1.62
    にほんブログ村
    -1.58
     you
    -1.50
     some
    -1.49
     will
    -1.48
     things
    -1.48
    POSITIVE LOGITS
    sufficient
    1.56
     チャーム
    1.55
     herbes
    1.48
     alho
    1.44
     salade
    1.43
    ︐
    1.40
     cuit
    1.40
     kultury
    1.39
     maïs
    1.38
     douze
    1.37
    Activations Density 0.206%

    No Known Activations