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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 10974
    Prev
    Next
    INDEX
    Explanations

    scraping data

    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
    ع
    2.84
    นั้น
    2.27
    та
    2.20
    И
    2.17
    не
    2.11
    ları
    2.11
    ли
    2.06
    nya
    2.03
    ري
    2.02
    时候
    2.02
    POSITIVE LOGITS
     reefs
    1.86
     plaques
    1.77
     mobiles
    1.75
     varieties
    1.73
     canisters
    1.69
     melodies
    1.66
    DTD
    1.66
     neoplasms
    1.65
    鼹
    1.64
     railroads
    1.63
    Activations Density 0.020%

    No Known Activations