© 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. 107881
    Prev
    Next
    INDEX
    Explanations

    support

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

    numbers and technical units

    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
     EVERY
    0.56
     imati
    0.52
     КАК
    0.50
     spéc
    0.50
    𝔪
    0.49
    참
    0.49
     এভাবে
    0.49
     avevano
    0.48
     lorf
    0.48
    𒈥
    0.48
    POSITIVE LOGITS
    elsius
    0.43
     ແ
    0.42
    RequestHandler
    0.42
    栋
    0.41
    dot
    0.40
    ilde
    0.40
    、
    0.40
    dan
    0.39
    Force
    0.39
    Endpoint
    0.39
    Activations Density 0.000%

    No Known Activations