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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B
    3. 41-GEMMASCOPE-2-RES-262K
    4. 241282
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
     Scientology
    0.64
     BIRTH
    0.58
     birth
    0.57
     zwe
    0.55
    genesis
    0.55
     प
    0.55
     Ther
    0.54
    முறை
    0.54
     უკ
    0.53
     Womens
    0.53
    POSITIVE LOGITS
    kas
    0.57
    搀
    0.56
    ną
    0.55
    illus
    0.54
     excitations
    0.54
    ناها
    0.53
    domains
    0.53
    㔹
    0.53
     licences
    0.52
    诱
    0.52
    Activations Density 0.000%

    No Known Activations