© 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. 212447
    Prev
    Next
    INDEX
    Explanations

    Microsoft

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

    electricity

    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
     Indexed
    0.47
     المعد
    0.46
    了一些
    0.44
    擞
    0.44
    enem
    0.43
     Sharks
    0.42
    ަލ
    0.42
     家
    0.41
     mơ
    0.41
    Ϩ
    0.41
    POSITIVE LOGITS
     காவல்
    0.49
     Marxist
    0.47
    chitz
    0.46
    ról
    0.46
     increments
    0.45
    ของการ
    0.45
    ══
    0.44
     impot
    0.44
     режисс
    0.44
    วรร
    0.44
    Activations Density 0.000%

    No Known Activations