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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 41-GEMMASCOPE-2-RES-65K
    4. 14346
    Prev
    Next
    INDEX
    Explanations

    data analysis reporting

    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
     государ
    0.59
    的历史
    0.56
     zeg
    0.55
     Beard
    0.55
    歷史
    0.55
    രുന്ന
    0.54
     historii
    0.54
    取
    0.54
    नोमियल
    0.53
    itioners
    0.53
    POSITIVE LOGITS
    ento
    0.56
    τίας
    0.54
    apit
    0.54
    Karl
    0.53
    entos
    0.52
    acular
    0.52
     tanha
    0.49
    ්
    0.49
     disp
    0.48
    bek
    0.48
    Activations Density 0.000%

    No Known Activations