© 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. 8067
    Prev
    Next
    INDEX
    Explanations

    chapter headings

    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
     և
    1.86
    да
    1.82
    เรา
    1.69
    こちらの
    1.68
     rẻ
    1.61
     وي
    1.54
     पाह
    1.52
    ם
    1.52
    ありません
    1.52
     desenvolv
    1.51
    POSITIVE LOGITS
    ان
    1.85
     elastomers
    1.81
    во
    1.80
    َ
    1.80
    ofthe
    1.77
     emeritus
    1.70
     זאת
    1.65
     spinors
    1.63
     filas
    1.61
    ال
    1.60
    Activations Density 0.062%

    No Known Activations