© 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. 119745
    Prev
    Next
    INDEX
    Explanations

    Eid holidays and greetings

    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
     is
    -1.92
    er
    -1.90
     which
    -1.86
     are
    -1.86
     has
    -1.77
    );
    -1.74
    f
    -1.71
    '
    -1.67
    ,"
    -1.64
     these
    -1.63
    POSITIVE LOGITS
     Houſe
    1.72
    瑷
    1.63
    capacete
    1.57
    jaqueta
    1.56
    顗
    1.52
     době
    1.51
     muelle
    1.49
    夲
    1.46
    鞣
    1.46
    راسیون
    1.45
    Activations Density 0.004%

    No Known Activations