© 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. 19584
    Prev
    Next
    INDEX
    Explanations

    other than what

    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
    zember
    -1.41
    夘
    -1.39
     приготовить
    -1.35
     also
    -1.34
     kangaroo
    -1.30
    aterdag
    -1.29
    seamnă
    -1.27
     أكثر
    -1.27
     trecut
    -1.26
     Mô
    -1.25
    POSITIVE LOGITS
     those
    1.78
     that
    1.68
     one
    1.67
     ones
    1.59
     two
    1.33
     assessing
    1.32
     being
    1.31
    begin
    1.30
     using
    1.28
     at
    1.26
    Activations Density 0.112%

    No Known Activations