© 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. 34327
    Prev
    Next
    INDEX
    Explanations

    specific medical terms

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

    train seating types

    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
    GLIGENCE
    0.47
     문서
    0.46
     суток
    0.45
    은
    0.44
     implicit
    0.44
     onFailure
    0.44
    ्यालय
    0.43
    자인
    0.42
    작
    0.42
     문화
    0.42
    POSITIVE LOGITS
    steroidal
    0.47
     અથવા
    0.47
    ipset
    0.47
     lotions
    0.46
     প্রত্যেক
    0.45
    slides
    0.45
    lookandfeel
    0.45
     whenever
    0.44
     aján
    0.44
     veya
    0.44
    Activations Density 0.000%

    No Known Activations