© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 40334
    Prev
    Next
    INDEX
    Explanations

    icons and file paths

    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
    Negative Logits
    م
    1.14
     기존
    0.95
    خدم
    0.90
    もう
    0.88
    من
    0.87
    IS
    0.86
    発生
    0.86
    AL
    0.85
    وف
    0.84
    НА
    0.82
    POSITIVE LOGITS
    aient
    1.15
    đenja
    1.07
    ेक्स
    1.05
    et
    1.02
    jarah
    1.01
    ierung
    0.98
    )>
    0.98
    uettes
    0.98
    oł
    0.97
    hasOwnProperty
    0.96
    Activations Density 0.000%

    No Known Activations