© 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-262K
    7. 241423
    Prev
    Next
    INDEX
    Explanations

    binary

    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_262k_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
    သေး
    0.64
     рассчиты
    0.62
     tuberculous
    0.61
     डेफ
    0.57
    ienste
    0.57
     설계
    0.56
    뢨
    0.55
     तया
    0.55
     glTex
    0.55
     টে
    0.55
    POSITIVE LOGITS
    binary
    0.57
    BINARY
    0.55
    भावना
    0.55
    慄
    0.54
    mathbb
    0.51
     pand
    0.51
     aberration
    0.50
    colspan
    0.50
    ALERT
    0.50
     demean
    0.50
    Activations Density 0.001%

    No Known Activations