© 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. 14883
    Prev
    Next
    INDEX
    Explanations

    HTML code

    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
    FeatureFlags
    0.56
     ख़बर
    0.56
     _
    0.55
    swire
    0.55
    āja
    0.55
     Morel
    0.55
     Rothschild
    0.55
    _${
    0.55
     Sawyer
    0.54
     _$
    0.54
    POSITIVE LOGITS
    topnav
    0.90
     tabela
    0.73
    WELCOME
    0.73
    NaOH
    0.72
     جدول
    0.72
     pusat
    0.71
    CENTR
    0.71
    表格
    0.70
    marquee
    0.70
    Catagory
    0.70
    Activations Density 0.003%

    No Known Activations