© 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. 84626
    Prev
    Next
    INDEX
    Explanations

    california surfer

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

    lists of things or people

    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
     ท
    0.56
     loosing
    0.55
    ependant
    0.48
     arrears
    0.46
     equipments
    0.45
     which
    0.45
     cca
    0.44
     reflexion
    0.44
     UAE
    0.44
    產生
    0.43
    POSITIVE LOGITS
     वगैरह
    0.68
     etcétera
    0.59
     ostensibly
    0.55
     voilà
    0.55
     esche
    0.54
    锃
    0.53
     quizá
    0.52
    やら
    0.51
     whatnot
    0.51
     deftly
    0.49
    Activations Density 0.099%

    No Known Activations