© 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. 55958
    Prev
    Next
    INDEX
    Explanations

    other words 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
     chronic
    0.43
    toothbrush
    0.43
    adamente
    0.41
    subdirectory
    0.41
    änd
    0.39
     alopecia
    0.39
     امرأة
    0.39
     subdirectory
    0.38
    ،
    0.38
    鞄
    0.38
    POSITIVE LOGITS
     autre
    0.53
     ouverture
    0.49
     ouvrir
    0.46
     newValue
    0.46
     permettent
    0.43
     identique
    0.43
    ല്ലാത്ത
    0.42
     autres
    0.42
     ورک
    0.42
     ajout
    0.42
    Activations Density 0.002%

    No Known Activations