© 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. 30828
    Prev
    Next
    INDEX
    Explanations

    Biennial, Bahia, Year, Continuous

    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
    ую
    1.39
    お金
    1.38
    ល្អ
    1.29
    お
    1.29
    ်
    1.27
     🤗
    1.27
    એ
    1.23
    при
    1.23
    最早
    1.23
    お届け
    1.22
    POSITIVE LOGITS
    ب
    1.54
    ী
    1.52
    ஷ்
    1.45
    vär
    1.41
     আবারো
    1.40
    ться
    1.35
    т
    1.34
     Архі
    1.33
    tiden
    1.33
    嵘
    1.33
    Activations Density 0.000%

    No Known Activations