© 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. 102121
    Prev
    Next
    INDEX
    Explanations

    some of the

    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
    You
    -1.54
    ’，
    -1.52
     Ն
    -1.41
    原谅
    -1.41
     deixe
    -1.41
     primeiras
    -1.38
     there
    -1.37
    遲
    -1.37
    even
    -1.34
     bús
    -1.32
    POSITIVE LOGITS
    ;
    1.50
     from
    1.45
    indelijk
    1.41
     [];
    1.40
    );
    1.38
     Diputados
    1.34
     are
    1.31
     on
    1.31
    都不能
    1.30
    เขา
    1.24
    Activations Density 0.022%

    No Known Activations