© 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. 142473
    Prev
    Next
    INDEX
    Explanations

    normally daily emphasis

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

    management understanding

    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
    Z
    0.57
    NO
    0.54
    0
    0.52
    M
    0.52
    neq
    0.51
    X
    0.50
    NA
    0.49
     (
    0.49
    add
    0.49
    name
    0.48
    POSITIVE LOGITS
    èque
    0.56
     Peu
    0.50
     Jeu
    0.49
     étoile
    0.49
     coldest
    0.49
     γίνεται
    0.48
     Montserrat
    0.48
     Grenzen
    0.47
     შემთ
    0.47
     Código
    0.46
    Activations Density 0.001%

    No Known Activations