© 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. 59401
    Prev
    Next
    INDEX
    Explanations

    actions 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
    7
    -1.96
     الذي
    -1.94
    8
    -1.89
    Karakteristik
    -1.88
    jednoc
    -1.88
     of
    -1.81
    趼
    -1.80
     parfüm
    -1.73
    Arduino
    -1.70
     mogli
    -1.70
    POSITIVE LOGITS
     There
    2.17
     then
    1.94
     into
    1.92
     about
    1.86
     like
    1.72
    🥂
    1.64
    🥰
    1.63
     encontraba
    1.62
     感じ
    1.59
     believed
    1.59
    Activations Density 0.382%

    No Known Activations