© 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. 241366
    Prev
    Next
    INDEX
    Explanations

    weights

    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
    ॕ
    0.64
    cex
    0.63
     الغير
    0.61
     Redox
    0.60
     रे
    0.59
    🌰
    0.58
     nonEmpty
    0.57
     ಕೇಂದ್ರ
    0.57
    득
    0.57
     촬영
    0.57
    POSITIVE LOGITS
     choice
    0.55
    doi
    0.54
    رات
    0.54
    AIDS
    0.54
     choices
    0.53
     about
    0.52
    さん
    0.52
    約
    0.51
     AIDS
    0.51
     Buddhist
    0.51
    Activations Density 0.001%

    No Known Activations