© 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. 211624
    Prev
    Next
    INDEX
    Explanations

    limitations and intents

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

    synthetic data generation

    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
    י
    0.56
    ي
    0.52
    спользование
    0.48
     predictability
    0.47
    OLIS
    0.47
    לה
    0.46
     conseguenza
    0.46
    ZIONE
    0.45
     forerunner
    0.45
    seca
    0.44
    POSITIVE LOGITS
     രാഷ്ട്ര
    0.51
    涕
    0.48
    antry
    0.48
     Pitch
    0.48
     तहरीर
    0.47
    LightTheme
    0.47
     कंट
    0.45
     Protocol
    0.45
     состояния
    0.45
    ডিট
    0.45
    Activations Density 0.000%

    No Known Activations