© 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
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 14206
    Prev
    Next
    INDEX
    Explanations

    data integration

    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
     therefore
    0.56
     {};
    0.54
    ({});
    0.54
     \(
    0.54
     solvers
    0.52
     explaining
    0.52
     reused
    0.52
     fights
    0.51
     Richardson
    0.51
     fighting
    0.50
    POSITIVE LOGITS
     ←
    0.77
    ←
    0.67
     ◆
    0.66
     ≠
    0.61
     〈
    0.61
    上市公司
    0.58
    ṱ
    0.55
    стоян
    0.54
     নি
    0.52
    そうな
    0.52
    Activations Density 0.000%

    No Known Activations