© 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. 14464
    Prev
    Next
    INDEX
    Explanations

    clarification

    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
    ।*
    0.70
    .•
    0.64
    দারি
    0.63
    »;
    0.61
    پرس
    0.58
     ചെയ്ത
    0.56
    »،
    0.56
    تبط
    0.55
     tortillas
    0.54
    .¹
    0.53
    POSITIVE LOGITS
    clar
    0.63
    Clar
    0.60
     favour
    0.57
     clarifying
    0.56
     Clar
    0.56
     clarification
    0.56
    シャン
    0.55
     MS
    0.54
    MS
    0.54
    centred
    0.54
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.