© 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. 182458
    Prev
    Next
    INDEX
    Explanations

    competitions for prizes

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

    moral principles

    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
    诗
    0.50
    나무
    0.47
    ém
    0.46
    港
    0.43
    汤
    0.43
    榜
    0.42
    语言
    0.42
     Oatmeal
    0.42
    知道
    0.41
    uí
    0.41
    POSITIVE LOGITS
    たとえば
    0.50
    for
    0.50
     ligament
    0.49
     radicals
    0.46
     cytokinin
    0.46
     articular
    0.46
     dimaksud
    0.46
    orable
    0.46
    例えば
    0.46
     ܕ
    0.45
    Activations Density 0.001%

    No Known Activations