© 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. 14854
    Prev
    Next
    INDEX
    Explanations

    /

    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
    id
    0.62
    /
    0.62
    걍
    0.61
    。
    0.60
    [],
    0.58
     ，
    0.58
    .
    0.56
    ±
    0.56
    and
    0.55
    akk
    0.55
    POSITIVE LOGITS
     posters
    1.00
     Posters
    0.95
     पोस्टर
    0.79
     картины
    0.74
     imagens
    0.72
     Paintings
    0.72
     تصاویر
    0.71
     poster
    0.70
     Maps
    0.70
     चित्रों
    0.70
    Activations Density 0.000%

    No Known Activations