© 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. 79633
    Prev
    Next
    INDEX
    Explanations

    suggests that

    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
    姈
    -1.41
    νες
    -1.39
     उनके
    -1.38
    gewiesen
    -1.30
     таком
    -1.28
     этом
    -1.27
     их
    -1.27
    erapeutics
    -1.23
    aş
    -1.22
    ⾯
    -1.22
    POSITIVE LOGITS
     that
    2.89
     a
    2.45
     an
    1.83
     something
    1.63
     ,
    1.41
     löyty
    1.40
     todella
    1.38
    にほんブログ村
    1.34
     começo
    1.34
     :
    1.30
    Activations Density 0.033%

    No Known Activations