© 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. 15158
    Prev
    Next
    INDEX
    Explanations

    code punctuation

    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
     えっと
    0.77
     って
    0.75
     ऑफिश
    0.73
     ましょう
    0.73
     $(".
    0.72
     ぐらい
    0.72
     ﺍﻟ
    0.72
     こと
    0.70
    |।
    0.70
     さん
    0.70
    POSITIVE LOGITS
    sl
    0.55
    ß
    0.54
    ंगे
    0.50
    KPI
    0.49
    ставьте
    0.49
    менен
    0.49
    suits
    0.48
    詳
    0.48
    宰
    0.48
    ः
    0.48
    Activations Density 0.008%

    No Known Activations