© 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. 7726
    Prev
    Next
    INDEX
    Explanations

    syndrome

    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
    да
    2.20
     зрения
    1.73
    ları
    1.73
    วน
    1.73
     isometry
    1.72
     wits
    1.67
    dır
    1.65
    ྫ
    1.63
    ።
    1.59
    larımız
    1.58
    POSITIVE LOGITS
    UT
    2.59
    ک
    2.23
    IN
    2.22
    OS
    2.14
    IR
    2.09
    CA
    2.09
    BA
    2.03
    J
    2.03
    ET
    2.02
    I
    1.95
    Activations Density 0.002%

    No Known Activations