© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 198632
    Prev
    Next
    INDEX
    Explanations

    programming, science, and professional roles

    np_acts-logits-general · gemini-2.5-flash-lite

    prevalent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    map
    0.46
     countably
    0.46
    of
    0.45
    ofil
    0.45
     Strokes
    0.44
    туга
    0.44
     Netflix
    0.43
     Contour
    0.41
     four
    0.40
     i
    0.39
    POSITIVE LOGITS
     enemigo
    0.56
    ATHER
    0.54
    ASER
    0.54
    ROOM
    0.52
     equipo
    0.52
    OSU
    0.52
     insanın
    0.51
     कमरे
    0.49
     ensinar
    0.48
     huesos
    0.48
    Activations Density 0.000%

    No Known Activations