© 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. 56801
    Prev
    Next
    INDEX
    Explanations

    wheelchairs or stroller

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

    four Pomodoro

    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
     bury
    0.52
    ᱙
    0.50
     მიმოწერა
    0.50
     學
    0.48
     synchronization
    0.48
    觀
    0.48
     ܐ
    0.47
     stare
    0.47
    üsseldorf
    0.46
     JULY
    0.46
    POSITIVE LOGITS
    нести
    0.50
     Chu
    0.47
     Lied
    0.46
    Holder
    0.46
     effectively
    0.45
    ↵↵
    0.45
    effectively
    0.45
    "
    0.43
    杷
    0.43
    ultra
    0.43
    Activations Density 0.000%

    No Known Activations