© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 153498
    Prev
    Next
    INDEX
    Explanations

    highest possible

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

    Nepal, Burns, Prometheus, partner, Entities

    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
     ט
    0.61
     пон
    0.55
     жи
    0.50
     д
    0.48
     rež
    0.48
     наси
    0.47
     знает
    0.47
     Asylum
    0.46
    <unused40>
    0.46
     ше
    0.45
    POSITIVE LOGITS
    raster
    0.48
    ΤΑ
    0.46
    rically
    0.46
    ഗത
    0.45
    이지만
    0.44
    컴
    0.44
    apture
    0.44
    otypes
    0.43
    regulating
    0.42
    rides
    0.42
    Activations Density 0.000%

    No Known Activations