© 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. 193412
    Prev
    Next
    INDEX
    Explanations

    religious concepts and dating

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

    economic, technical, or creative domains

    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
     that
    0.52
     kiles
    0.48
    간
    0.47
     antagonists
    0.47
    gom
    0.46
     indicates
    0.45
    みを
    0.45
     facades
    0.45
    அந்த
    0.44
     indicating
    0.44
    POSITIVE LOGITS
     Linz
    0.47
     ز
    0.47
     रोटी
    0.46
     የበለጠ
    0.45
     प्रमुख
    0.44
    شت
    0.44
     مقدس
    0.44
     উত্তরা
    0.43
     remboursement
    0.43
     roto
    0.42
    Activations Density 0.000%

    No Known Activations