Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B
    3. 41-GEMMASCOPE-2-RES-262K
    4. 241154
    Prev
    Next
    INDEX
    Explanations

    API endpoints

    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
    inheritDoc
    0.71
    珩
    0.70
    ۣ
    0.66
    伦
    0.63
    仡
    0.63
    芃
    0.63
     qubit
    0.63
    苾
    0.63
    Polygon
    0.62
     neutroph
    0.61
    POSITIVE LOGITS
    RequestMapping
    1.61
    ResponseBody
    0.69
    Mappings
    0.69
     reactionary
    0.67
     राजीव
    0.67
     Sark
    0.66
    ramework
    0.66
     rah
    0.66
     रैंकिंग
    0.66
     rhe
    0.65
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.