© 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. 72698
    Prev
    Next
    INDEX
    Explanations

    foreign names and scripts

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

    army of, for higher, Nvidia DL, stocks offer, forget your, tickets booked

    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
    ونه
    0.46
    ندا
    0.46
    楓
    0.46
    طب
    0.45
    ورد
    0.45
     Paperback
    0.44
    什麼
    0.43
    شع
    0.43
     وض
    0.42
    هل
    0.40
    POSITIVE LOGITS
     봉
    0.50
     メガネ
    0.49
    まつ
    0.48
    atelier
    0.47
     সহায়তা
    0.46
    homeini
    0.45
    nuevo
    0.45
     ಮೇಲೆ
    0.44
     ಜಾ
    0.44
    ંટણી
    0.44
    Activations Density 0.001%

    No Known Activations