© 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. 232442
    Prev
    Next
    INDEX
    Explanations

    savings initiatives

    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
     временем
    0.49
     sched
    0.46
     manuss
    0.45
    ۵
    0.44
    吭
    0.44
    ására
    0.43
    dagen
    0.43
     fehl
    0.42
     фильмов
    0.42
    时间的
    0.41
    POSITIVE LOGITS
    Colonne
    0.57
    𝘵
    0.50
     BE
    0.48
     outermost
    0.47
    CE
    0.46
    BE
    0.46
    توان
    0.46
     PEOPLE
    0.46
    𝗮
    0.46
     extinguish
    0.46
    Activations Density 0.001%

    No Known Activations