© 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. 12043
    Prev
    Next
    INDEX
    Explanations

    related field

    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
    ters
    1.05
     of
    1.05
     Politique
    1.04
    vation
    1.02
    arı
    1.02
    та
    1.01
    রূপে
    0.95
    δήποτε
    0.94
     Lagrange
    0.91
    ़
    0.91
    POSITIVE LOGITS
    이라면
    0.92
    де
    0.91
    Ф
    0.90
    mutation
    0.87
    ેલ
    0.84
     vinto
    0.84
    Pokud
    0.84
    ON
    0.83
    BatchNorm
    0.83
     berusia
    0.83
    Activations Density 0.000%

    No Known Activations