© 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. 99166
    Prev
    Next
    INDEX
    Explanations

    enjoys doing 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
     they
    -2.00
     a
    -1.71
     others
    -1.68
     mūsų
    -1.52
     as
    -1.50
     their
    -1.46
     some
    -1.45
     our
    -1.42
     maž
    -1.39
     most
    -1.37
    POSITIVE LOGITS
     and
    1.67
     medes
    1.66
     to
    1.64
     renon
    1.59
     ͡°
    1.52
     revanche
    1.50
    gestaltung
    1.48
    ＄
    1.48
     but
    1.43
    鉏
    1.43
    Activations Density 0.020%

    No Known Activations