© 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. 67356
    Prev
    Next
    INDEX
    Explanations

    business affairs and activities

    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
    鈊
    -2.47
    蟊
    -2.27
    鱨
    -2.23
     bijna
    -2.16
     italiens
    -2.11
    螣
    -2.11
    趼
    -2.11
    jdons
    -2.09
     dégust
    -2.09
     dégâts
    -2.06
    POSITIVE LOGITS
    “
    2.70
    ing
    2.63
    le
    2.20
    ?”
    2.09
    x
    2.03
    ",
    2.00
    n
    1.90
    l
    1.88
    верху
    1.87
     Of
    1.86
    Activations Density 0.003%

    No Known Activations