© 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. 91776
    Prev
    Next
    INDEX
    Explanations

    mathematical sequences and series

    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
     not
    -1.31
     does
    -0.99
     striving
    -0.96
     what
    -0.94
     after
    -0.93
     seemingly
    -0.90
     where
    -0.88
     Although
    -0.87
     Since
    -0.86
     did
    -0.86
    POSITIVE LOGITS
    也要
    1.05
     momentous
    0.99
     fl
    0.97
    ‘‘
    0.96
    Gandhi
    0.96
    ‘’
    0.95
     ț
    0.93
    tings
    0.91
    stery
    0.91
    selbe
    0.91
    Activations Density 0.037%

    No Known Activations