© 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. 63772
    Prev
    Next
    INDEX
    Explanations

    potential outcomes or effects

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

    policy, influence, and popular adoption

    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
    рах
    0.46
    omyces
    0.45
    ᵛ
    0.44
     Zusätzlich
    0.44
     அமில
    0.44
    喈
    0.43
    ılım
    0.42
     труб
    0.42
     تست
    0.42
    Intersection
    0.42
    POSITIVE LOGITS
    (
    0.52
     ginseng
    0.49
     childbirth
    0.49
     mandatory
    0.49
     steaming
    0.49
     botanique
    0.48
     sloppy
    0.47
     opcao
    0.47
     segregation
    0.46
     penalty
    0.46
    Activations Density 0.000%

    No Known Activations