© 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. 22471
    Prev
    Next
    INDEX
    Explanations

    following common words

    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
    ↵
    -1.63
    日時
    -1.45
    因為
    -1.41
     这
    -1.35
    ↵↵
    -1.34
     ciebie
    -1.32
     –
    -1.32
    stddef
    -1.30
     ménages
    -1.30
     poignée
    -1.29
    POSITIVE LOGITS
     fizik
    1.51
     pudieron
    1.40
     ané
    1.39
     DEBUG
    1.36
    setMinimum
    1.34
     hubieran
    1.34
     Singapura
    1.33
     duiz
    1.31
    tilling
    1.31
    THEW
    1.30
    Activations Density 0.321%

    No Known Activations