© 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. 221323
    Prev
    Next
    INDEX
    Explanations

    provides functionality

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

    What's good?

    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
    to
    0.66
    c
    0.62
    the
    0.61
    download
    0.57
    O
    0.57
    t
    0.55
    as
    0.54
    do
    0.54
    people
    0.54
    ng
    0.54
    POSITIVE LOGITS
     gravid
    0.54
     classy
    0.52
     grapefruit
    0.52
     могла
    0.50
     brighten
    0.49
     carcinoma
    0.49
     rocked
    0.48
    ጋገብ
    0.48
    典型的
    0.47
     könnten
    0.47
    Activations Density 0.000%

    No Known Activations