© 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. 193062
    Prev
    Next
    INDEX
    Explanations

    so you or additional charge

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

    competition, tension, inflation, diabetes, alcohol

    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
    Negative Logits
    ם
    0.48
    seh
    0.47
    т
    0.47
    н
    0.46
    ו
    0.42
     Миха
    0.42
    ieh
    0.42
    нибудь
    0.42
    FIN
    0.42
    к
    0.42
    POSITIVE LOGITS
     a
    0.48
     aneur
    0.46
     hydrangea
    0.46
     aneurysm
    0.45
     cnc
    0.45
     rebound
    0.44
     proverb
    0.44
     synov
    0.44
     morf
    0.44
     mousse
    0.43
    Activations Density 0.000%

    No Known Activations