© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 81582
    Prev
    Next
    INDEX
    Explanations

    discovers, measures, scenarios, complexity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    カバー
    0.52
     actes
    0.52
     blancs
    0.49
     eaters
    0.46
    仕事
    0.46
    $=
    0.46
     iguales
    0.45
     wears
    0.45
    ן
    0.45
     extrémités
    0.44
    POSITIVE LOGITS
    sburg
    0.50
    nya
    0.49
    ný
    0.49
    kör
    0.47
     IOException
    0.45
    n
    0.44
    bery
    0.44
     superconduct
    0.44
    াজা
    0.44
    erver
    0.44
    Activations Density 0.001%

    No Known Activations