© 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. 211938
    Prev
    Next
    INDEX
    Explanations

    http://

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

    identifying programming languages using keywords

    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
    tır
    0.59
     고객
    0.54
     стрем
    0.54
    Virtualized
    0.54
    OCK
    0.53
     определён
    0.53
     약간
    0.52
    獧
    0.52
     کشاور
    0.52
     مشتری
    0.51
    POSITIVE LOGITS
     Class
    0.55
     Communications
    0.52
     showers
    0.52
     slides
    0.52
     rides
    0.51
     seaw
    0.50
     per
    0.49
     communications
    0.49
     guides
    0.48
     seals
    0.48
    Activations Density 0.000%

    No Known Activations