© 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. 1207
    Prev
    Next
    INDEX
    Explanations

    specific leading words and codes

    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
    selfobj
    0.32
    $)$.
    0.29
    रावर
    0.27
    Hfn
    0.27
    ampaikan
    0.27
    logrus
    0.27
    sadquotes
    0.27
    acchati
    0.26
    .³
    0.26
     Ciebie
    0.26
    POSITIVE LOGITS
     other
    0.41
     also
    0.39
     کے
    0.31
     to
    0.31
     другие
    0.31
     lainnya
    0.30
     otros
    0.29
     andere
    0.29
     inoltre
    0.29
     के
    0.28
    Activations Density 0.297%

    No Known Activations