© 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. 123971
    Prev
    Next
    INDEX
    Explanations

    essay about

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

    #include <stdlib.h>

    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
     arches
    0.57
     ventilators
    0.54
     triads
    0.52
    следова
    0.49
    รถ
    0.48
     tyr
    0.47
     audits
    0.47
    頸
    0.47
     архитек
    0.46
     arch
    0.46
    POSITIVE LOGITS
    下标
    0.47
     brunâtre
    0.46
    تی
    0.46
    TAG
    0.46
     회사
    0.46
    azione
    0.44
    Song
    0.44
     关于
    0.43
    R
    0.43
    单位
    0.43
    Activations Density 0.000%

    No Known Activations