© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 13703
    Prev
    Next
    INDEX
    Explanations

    selenium

    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
     درج
    0.59
    कानेर
    0.55
    族的
    0.53
    哉
    0.53
     dependency
    0.52
    BMW
    0.52
     dependence
    0.51
     доро
    0.50
    udir
    0.49
     dependencies
    0.49
    POSITIVE LOGITS
    wire
    0.75
     Wire
    0.61
     wire
    0.60
    onsen
    0.57
     краси
    0.56
     아름
    0.56
    缆
    0.55
    WIRE
    0.54
    tower
    0.53
    beautiful
    0.53
    Activations Density 0.000%

    No Known Activations