© 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. 15036
    Prev
    Next
    INDEX
    Explanations

    partly months

    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
    カット
    0.56
    ɺ
    0.54
    rono
    0.53
    ROME
    0.53
    ře
    0.52
    ilde
    0.50
    தோ
    0.49
    ="#"
    0.49
    bara
    0.49
    olgens
    0.49
    POSITIVE LOGITS
     частично
    0.63
     Jacks
    0.57
     jacks
    0.55
     месяц
    0.54
     months
    0.54
    ∂</
    0.53
     ምክ
    0.53
     музыкан
    0.52
     Partially
    0.52
     partly
    0.52
    Activations Density 0.000%

    No Known Activations