© 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. 192330
    Prev
    Next
    INDEX
    Explanations

    given antibiotics and biofeedback

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

    IoT, accounts, stories, creatures

    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
    يها
    0.58
    মেল
    0.55
    жая
    0.52
    筤
    0.50
    вав
    0.50
     دهد
    0.50
     выбран
    0.49
    wijl
    0.49
    товый
    0.49
    рисов
    0.49
    POSITIVE LOGITS
     galaxies
    0.51
     obe
    0.51
     cinemas
    0.49
     governments
    0.48
     ZZ
    0.48
     chromosomes
    0.46
    Η
    0.46
     Ades
    0.46
     stably
    0.46
     os
    0.46
    Activations Density 0.000%

    No Known Activations