© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 7218
    Prev
    Next
    INDEX
    Explanations

    theoretical ideal

    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
    ين
    1.95
    یا
    1.77
    я
    1.68
    ною
    1.66
    ро
    1.59
    та
    1.55
    स्परिक
    1.53
    限于
    1.52
     maven
    1.42
    前端
    1.41
    POSITIVE LOGITS
    solutions
    2.03
    de
    1.83
     Hemos
    1.83
    AST
    1.66
    e
    1.59
    sell
    1.57
    क्ष्य
    1.57
    غ
    1.57
    ي
    1.56
     وبركاته
    1.55
    Activations Density 0.048%

    No Known Activations