© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 12380
    Prev
    Next
    INDEX
    Explanations

    software, tech, and specific product names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     डॉक्टर
    1.09
     là
    1.04
     bị
    1.02
     не
    1.01
     বলে
    0.99
     defeated
    0.99
     прекра
    0.97
    কে
    0.94
    は
    0.92
    ਮ
    0.92
    POSITIVE LOGITS
    ာ
    1.07
    कूट
    0.95
    quela
    0.93
     semblance
    0.91
    ）.
    0.89
    at
    0.89
     tjen
    0.88
    >().
    0.86
    ()}")
    0.86
    ️
    0.86
    Activations Density 0.061%

    No Known Activations