Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 44733
    Prev
    Next
    INDEX
    Explanations

    Eastern Orthodox

    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
    ро
    1.77
    ię
    1.38
    IN
    1.19
    Л
    1.16
    ال
    1.11
    ोत्तम
    1.11
    тро
    1.10
    ل
    1.10
    ‌ی
    1.08
    INVEST
    1.08
    POSITIVE LOGITS
     వచ్చిన
    1.27
     πάντα
    1.19
    _);
    1.16
     گردد
    1.15
    --");
    1.14
     zippers
    1.13
    ுள்ளார்
    1.12
    彿
    1.07
     antica
    1.05
    끗
    1.04
    Activations Density 0.000%

    No Known Activations