© 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. 79378
    Prev
    Next
    INDEX
    Explanations

    explaining claims actions choices

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

    building, sensation, radiation, firing

    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
     dismin
    0.48
    减肥
    0.48
     diminu
    0.46
    怔
    0.45
     aument
    0.45
     الاستاذ
    0.45
    认
    0.44
     Atlet
    0.43
    惭
    0.43
     نتی
    0.43
    POSITIVE LOGITS
    собенно
    0.46
    色彩
    0.46
    has
    0.45
     wines
    0.44
    ষুধ
    0.43
     walls
    0.42
    DER
    0.42
     paints
    0.42
     painting
    0.42
    숯
    0.42
    Activations Density 0.000%

    No Known Activations