© 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. 207326
    Prev
    Next
    INDEX
    Explanations

    registered education plans

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

    spiritual and symbolic concepts

    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
    beit
    0.52
     إس
    0.48
     hosp
    0.47
    má
    0.47
     권
    0.46
     Ambiente
    0.45
     bestätigt
    0.45
    řich
    0.44
    fär
    0.44
    ២
    0.44
    POSITIVE LOGITS
    силання
    0.52
    сна
    0.50
    ώσεις
    0.50
    ায়ে
    0.48
    компа
    0.47
    то
    0.46
    виа
    0.46
    儷
    0.45
    有名な
    0.44
    нология
    0.43
    Activations Density 0.001%

    No Known Activations