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. 44736
    Prev
    Next
    INDEX
    Explanations

    css combinators

    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
    t
    2.67
    짙
    2.19
    ي
    1.81
    y
    1.74
    s
    1.69
    에
    1.63
    CameraOpened
    1.59
    tól
    1.56
    ت
    1.56
    د
    1.53
    POSITIVE LOGITS
    ্কার
    1.52
    끔
    1.39
    ιν
    1.30
    ر
    1.30
    FBSDKGraph
    1.30
    şe
    1.29
    ленні
    1.28
    вой
    1.27
     όχι
    1.27
    ҝ
    1.27
    Activations Density 0.000%

    No Known Activations