© 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. 7778
    Prev
    Next
    INDEX
    Explanations

    trading Friday

    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
     the
    -2.91
    岨
    -2.38
     verhind
    -2.19
    ⛦
    -2.14
     a
    -2.14
     può
    -2.13
    謌
    -2.09
     verschillende
    -2.06
    genodigd
    -2.06
    鹀
    -2.03
    POSITIVE LOGITS
     in
    2.31
     there
    2.30
     on
    2.17
    .
    2.11
    \
    2.08
    '
    2.08
     There
    1.97
    There
    1.95
     $
    1.85
     Since
    1.85
    Activations Density 0.137%

    No Known Activations