© 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. 85883
    Prev
    Next
    INDEX
    Explanations

    Big Daddy / device identifiers

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

    Universal Condemnation, Base URL, inconsistencies

    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
     sporty
    0.58
     Aquaculture
    0.55
    o
    0.55
    B
    0.52
    O
    0.52
    N
    0.52
     Sports
    0.50
    도
    0.50
    IN
    0.49
    H
    0.49
    POSITIVE LOGITS
     Пі
    0.56
     між
    0.53
     ပ
    0.52
     числен
    0.52
     同じ
    0.51
     μεταξύ
    0.51
     ଜ
    0.50
     നിന്നും
    0.50
     カップ
    0.49
    基金
    0.48
    Activations Density 0.000%

    No Known Activations