© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 15266
    Prev
    Next
    INDEX
    Explanations

    Flask

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kh
    0.63
    kh
    0.57
    Kh
    0.56
     canopy
    0.56
     Kh
    0.54
     광
    0.51
    .$(
    0.51
    czych
    0.50
    涧
    0.50
     convexes
    0.50
    POSITIVE LOGITS
     Flask
    2.02
    Flask
    1.98
     flask
    1.97
    flask
    1.92
     flasks
    1.57
    FlaskApp
    1.43
     SQLAlchemy
    1.34
    SQLALCHEMY
    1.25
     blueprint
    1.14
    jsonify
    1.14
    Activations Density 0.001%

    No Known Activations