© 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. 129011
    Prev
    Next
    INDEX
    Explanations

    function, brands, curiosity, material, shading, visitors, posting

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

    concepts and descriptions

    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
    ﺘ
    0.55
    currentPage
    0.52
    Ephemeral
    0.50
    Թ
    0.48
    OTHER
    0.47
    ג
    0.46
    TH
    0.46
    ENTAL
    0.46
    гах
    0.46
    ጥረ
    0.46
    POSITIVE LOGITS
     dérou
    0.48
     ضمن
    0.46
     ใหญ่
    0.45
    䂧
    0.44
     بل
    0.42
     Profiles
    0.41
     نزدیک
    0.41
     Big
    0.41
     CPC
    0.41
     dovet
    0.41
    Activations Density 0.002%

    No Known Activations