© 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. 172169
    Prev
    Next
    INDEX
    Explanations

    system discussions

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

    worms products and online membership

    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
    ↵
    0.50
    添
    0.45
    ink
    0.44
    恳
    0.43
    avis
    0.43
     Espero
    0.43
    dea
    0.42
    ving
    0.42
    my
    0.42
    kn
    0.42
    POSITIVE LOGITS
    Შ
    0.49
     десять
    0.48
    ཿ
    0.48
    леду
    0.48
     actuation
    0.47
     다섯
    0.46
     ofthe
    0.46
     monop
    0.46
     competencies
    0.46
    сибир
    0.45
    Activations Density 0.000%

    No Known Activations