© 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. 10-GEMMASCOPE-RES-131K
    7. 129183
    Prev
    Next
    INDEX
    Explanations

    count of charge

    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
    There
    -1.77
    Really
    -1.73
    THE
    -1.54
    However
    -1.50
    It
    -1.48
    '
    -1.48
     with
    -1.48
     paulo
    -1.47
    But
    -1.45
    Like
    -1.43
    POSITIVE LOGITS
     of
    2.22
    泐
    2.14
     they
    2.09
    翃
    1.58
     nears
    1.57
     critic
    1.57
     reiter
    1.52
    𖥧
    1.52
    fficients
    1.52
    ;%%
    1.52
    Activations Density 0.007%

    No Known Activations