© 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. 14926
    Prev
    Next
    INDEX
    Explanations

    principles

    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
    背景
    0.75
    目的
    0.65
    概述
    0.64
     事業
    0.63
    requency
    0.63
    球员
    0.63
    値
    0.62
    Không
    0.62
    }|^
    0.61
    redirectTo
    0.61
    POSITIVE LOGITS
     Eco
    0.65
     eco
    0.63
    Eco
    0.59
     ECO
    0.58
    inch
    0.55
    eco
    0.55
     Boh
    0.55
    clf
    0.54
     assuming
    0.53
    ää
    0.52
    Activations Density 0.000%

    No Known Activations