© 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. 748
    Prev
    Next
    INDEX
    Explanations

    code and music notation

    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
    狗狗
    0.85
    ك
    0.82
    ف
    0.82
    Đây
    0.81
    ዚህ
    0.78
    ش
    0.78
    أ
    0.77
    ᑖ
    0.76
    ییر
    0.75
    ن
    0.73
    POSITIVE LOGITS
    рных
    0.81
    тный
    0.80
    మో
    0.79
     unix
    0.78
    жной
    0.77
    Proxy
    0.76
    тной
    0.76
    FileInputExcel
    0.73
     следующее
    0.73
    рное
    0.72
    Activations Density 0.000%

    No Known Activations