© 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. 67313
    Prev
    Next
    INDEX
    Explanations

    deemed beneficial, relevant, or permanent

    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
     outburst
    -3.06
     When
    -2.73
    arraycopy
    -2.69
    achios
    -2.66
    婠
    -2.61
    toThrow
    -2.59
     unwavering
    -2.58
    \">
    -2.56
     ткани
    -2.53
     сталь
    -2.50
    POSITIVE LOGITS
    '
    3.03
    {
    3.02
    えっ
    2.45
    是如何
    2.39
     parcialmente
    2.38
    出来た
    2.33
     réfugiés
    2.31
    和其他
    2.28
    出来て
    2.28
    うわ
    2.25
    Activations Density 0.003%

    No Known Activations