© 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-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 3622
    Prev
    Next
    INDEX
    Explanations

    between sets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    기
    0.80
    鲍
    0.77
    나
    0.75
    مة
    0.75
     operate
    0.75
    계를
    0.75
     encourage
    0.73
    ہ
    0.73
    ت
    0.73
     avanç
    0.72
    POSITIVE LOGITS
    ローチ
    0.79
    olov
    0.76
    ра
    0.75
    doors
    0.74
     വിള
    0.71
     loadings
    0.70
    而在
    0.69
    Kisi
    0.69
    дентификаторы
    0.69
    ex
    0.68
    Activations Density 0.000%

    No Known Activations