© 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. 79396
    Prev
    Next
    INDEX
    Explanations

    spectral ridges

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

    process or specification

    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
     जमा
    0.51
     शारीरिक
    0.50
     आवश्यकता
    0.49
     পত্র
    0.49
     આવેલા
    0.48
    umlu
    0.47
     छो
    0.47
     +=
    0.47
     Einwilligung
    0.46
     गावा
    0.46
    POSITIVE LOGITS
     spectral
    0.57
     ridges
    0.54
     slic
    0.52
     bridges
    0.51
     tungsten
    0.50
     aberration
    0.49
     matchups
    0.48
     mixt
    0.48
     sputter
    0.48
     subsurface
    0.47
    Activations Density 0.001%

    No Known Activations