© 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. 198648
    Prev
    Next
    INDEX
    Explanations

    free plastic or free entry

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

    describing qualities

    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
     parks
    0.50
    ５
    0.47
     optimizes
    0.46
     baik
    0.46
     os
    0.46
     Singapore
    0.45
     lasts
    0.45
    新加坡
    0.45
     th
    0.44
     e
    0.43
    POSITIVE LOGITS
     politic
    0.44
    が無い
    0.44
     clums
    0.44
    czyn
    0.43
    vadipine
    0.42
     روند
    0.42
     शख्स
    0.42
     რა
    0.41
    entropic
    0.41
     رف
    0.40
    Activations Density 0.001%

    No Known Activations