© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 24794
    Prev
    Next
    INDEX
    Explanations

    objects, groups, or concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     در
    0.41
    ickt
    0.41
     servicios
    0.40
     في
    0.39
     productos
    0.38
    ในการ
    0.38
     kebutuhan
    0.38
     آتے
    0.37
    </h1>
    0.37
     لپاره
    0.37
    POSITIVE LOGITS
    using
    0.41
    according
    0.40
    というのは
    0.38
    remember
    0.37
     reassuring
    0.37
    sqrt
    0.36
     Previous
    0.36
    ucceed
    0.36
    ัล
    0.36
    みが
    0.36
    Activations Density 0.089%

    No Known Activations