© 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. 117856
    Prev
    Next
    INDEX
    Explanations

    compatibility, window, process, accessibility

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

    infection and inflammation

    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
    کنند
    0.54
    ísk
    0.48
    ご了承ください
    0.48
    ៨
    0.48
    ходи
    0.48
    upakan
    0.47
     می‌کند
    0.47
    ៤
    0.47
     सम्पन्न
    0.47
     ചെയ്തു
    0.46
    POSITIVE LOGITS
     Amino
    0.50
     macho
    0.48
     NG
    0.46
     typ
    0.46
     desperate
    0.45
     Enhanced
    0.44
     Agra
    0.44
     Diamond
    0.44
     Easy
    0.43
     Albert
    0.43
    Activations Density 0.001%

    No Known Activations