© 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. 140071
    Prev
    Next
    INDEX
    Explanations

    end of

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

    pros and cons

    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
    کش
    0.57
    يه
    0.54
    مل
    0.54
    тие
    0.51
    USES
    0.50
    وع
    0.50
    وض
    0.50
    ش
    0.50
    ورو
    0.49
    USED
    0.49
    POSITIVE LOGITS
     вовсе
    0.46
    皋
    0.45
     завер
    0.44
     מד
    0.44
     characterizing
    0.44
    acchati
    0.44
     সমঝো
    0.43
     υπε
    0.43
    garakan
    0.43
    മാണ്
    0.42
    Activations Density 0.001%

    No Known Activations