© 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. 14030
    Prev
    Next
    INDEX
    Explanations

    C++ function definitions

    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
     merak
    -1.92
    ͛
    -1.90
     katk
    -1.71
    絝
    -1.69
     düğün
    -1.66
     abiye
    -1.64
     regresó
    -1.64
    ㅡ
    -1.63
     sokak
    -1.63
    邋
    -1.63
    POSITIVE LOGITS
     of
    1.97
     from
    1.94
     ‘
    1.80
    </em>
    1.77
     at
    1.74
     or
    1.73
     despite
    1.72
     häufigsten
    1.71
    ’
    1.70
     started
    1.66
    Activations Density 0.004%

    No Known Activations