© 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. 34-GEMMASCOPE-RES-131K
    7. 48797
    Prev
    Next
    INDEX
    Explanations

    document structure and formatting

    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_34/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
     also
    -0.82
    <strong>
    -0.80
    ;
    -0.80
    ÑOS
    -0.80
     (
    -0.79
    TypeList
    -0.79
    tizing
    -0.78
    {_
    -0.78
     Momente
    -0.77
    ;$
    -0.76
    POSITIVE LOGITS
    ↵↵
    1.15
    ↵↵↵
    1.11
    皆さま
    1.02
    Tämä
    1.00
    みなさん
    0.99
    adalupe
    0.97
    みなさま
    0.97
    onucleotides
    0.96
    Föld
    0.93
    Это
    0.92
    Activations Density 0.012%

    No Known Activations