© 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. 247050
    Prev
    Next
    INDEX
    Explanations

    trends and structure

    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
    Not in Any Lists

    No Comments

    Negative Logits
     බව
    0.48
    confident
    0.48
    SPRAY
    0.46
     RESEARCH
    0.45
     건축
    0.44
    कृपया
    0.44
     explique
    0.43
    ก
    0.43
     substantive
    0.43
     dereg
    0.42
    POSITIVE LOGITS
     небольшой
    0.49
     pequeños
    0.47
     小型
    0.47
    ської
    0.45
     ぐらい
    0.45
     両
    0.44
     Deps
    0.44
    зме
    0.44
    膂
    0.44
     kleinen
    0.43
    Activations Density 0.000%

    No Known Activations