© 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. 102847
    Prev
    Next
    INDEX
    Explanations

    defining roles and scopes

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

    user flow diagrams

    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
    ttes
    0.59
     ବ
    0.54
    ttt
    0.54
    vano
    0.53
    tta
    0.52
    titan
    0.50
    gies
    0.50
    kant
    0.49
     Inserting
    0.49
     ভে
    0.48
    POSITIVE LOGITS
     concordance
    0.49
     reproducibility
    0.46
     rectification
    0.46
    도
    0.46
     correspondence
    0.45
     barbar
    0.45
     dissonance
    0.44
     spotting
    0.44
     presentation
    0.44
    هور
    0.43
    Activations Density 0.000%

    No Known Activations