© 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. 12781
    Prev
    Next
    INDEX
    Explanations

    categories and descriptions

    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
     ମ
    0.57
     SqlConnection
    0.57
     Normdatei
    0.54
     rãi
    0.54
     полное
    0.53
    idental
    0.53
     मलया
    0.53
     Nautilus
    0.52
     год
    0.52
     यू
    0.52
    POSITIVE LOGITS
     demok
    0.55
    _{*
    0.54
     zon
    0.54
     البلد
    0.54
    richtungen
    0.52
     acuerdos
    0.52
    ison
    0.52
     اكتوبر
    0.52
     ",",
    0.52
    attform
    0.51
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.