© 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. 15303
    Prev
    Next
    INDEX
    Explanations

    sacrifice and costs

    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
     bal
    0.57
    ренных
    0.54
    Uuid
    0.53
    ㎎
    0.53
     gering
    0.53
    лос
    0.52
     bess
    0.52
    ഗണ
    0.52
    줌
    0.52
    lovepoetry
    0.50
    POSITIVE LOGITS
     simultaneously
    0.50
     Lives
    0.50
     facilities
    0.49
     مشتمل
    0.47
    yka
    0.46
    rą
    0.46
    ę
    0.46
    ‌تر
    0.46
    󠁴
    0.46
     costs
    0.46
    Activations Density 0.000%

    No Known Activations