© 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. 14860
    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
    EndInit
    0.41
    из
    0.36
    걍
    0.35
    겉
    0.35
    private
    0.34
    __
    0.33
    ครับ
    0.33
    উপ
    0.33
    นต์
    0.33
     приват
    0.32
    POSITIVE LOGITS
     refuses
    0.38
     swears
    0.37
     buckle
    0.36
     buckles
    0.36
     misses
    0.36
     CIRCU
    0.35
     कुत्ते
    0.35
     கூறியதாவது
    0.35
    韵
    0.35
     대한민국
    0.35
    Activations Density 0.000%

    No Known Activations