© 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. 34651
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ↵↵
    1.01
     akan
    1.00
     Akan
    0.97
     Amerika
    0.96
     dan
    0.94
     CH
    0.94
    Wouldn
    0.93
    、
    0.92
     W
    0.91
     WH
    0.91
    POSITIVE LOGITS
    ра
    0.92
    не
    0.90
    >`,
    0.88
    ൨
    0.87
    ímica
    0.87
    दो
    0.84
    lipped
    0.83
    ాలతో
    0.83
    レスレット
    0.82
    ovjek
    0.81
    Activations Density 0.017%

    No Known Activations