© 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. 8593
    Prev
    Next
    INDEX
    Explanations

    value of

    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
    ی
    2.30
    ில்
    2.23
    ال
    2.14
    ्य
    1.97
    لم
    1.95
    ین
    1.88
    ش
    1.88
    το
    1.86
    ى
    1.82
    र
    1.80
    POSITIVE LOGITS
     Enh
    2.11
    이죠
    2.02
    coelastic
    1.98
    केंसी
    1.96
    이라
    1.95
    acious
    1.89
    ژگی
    1.88
    theless
    1.80
     وفي
    1.79
    이란
    1.79
    Activations Density 0.502%

    No Known Activations