© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 31413
    Prev
    Next
    INDEX
    Explanations

    introducing an assumption

    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
    적인
    1.79
    нки
    1.79
    larını
    1.73
    tered
    1.68
    ্স
    1.66
    ב
    1.54
    yyyy
    1.50
    на
    1.48
    有什么
    1.48
    不管
    1.46
    POSITIVE LOGITS
    هور
    2.14
    ك
    1.99
    encia
    1.86
    ती
    1.71
    ни
    1.67
    ن
    1.67
    الصفحه
    1.66
    <0x98>
    1.58
     Automobiles
    1.57
     профессии
    1.57
    Activations Density 0.002%

    No Known Activations