© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76888
    Prev
    Next
    INDEX
    Explanations

    unsigned integer types

    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
     htons
    -0.95
     ushort
    -0.93
    ushort
    -0.91
    两
    -0.83
    ('../../
    -0.81
    TEEN
    -0.78
     XVI
    -0.77
    醛
    -0.75
    半
    -0.74
     dual
    -0.73
    POSITIVE LOGITS
     four
    1.31
     Four
    1.25
    Four
    1.23
    四个
    1.21
    four
    1.13
     quartet
    1.04
     fours
    1.00
     négy
    0.99
     Weekly
    0.99
     weekly
    0.99
    Activations Density 0.026%

    No Known Activations