© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 185032
    Prev
    Next
    INDEX
    Explanations

    spend less, their products

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

    musical approach

    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
    苎
    0.51
    বে
    0.47
     cifra
    0.46
    <0x99>
    0.43
     జా
    0.42
    कांक्षा
    0.42
     అస
    0.41
    лера
    0.41
    kem
    0.41
    propertyPath
    0.41
    POSITIVE LOGITS
    씐
    0.46
     말미암
    0.46
     OSI
    0.46
    ﻧ
    0.46
     nanocom
    0.45
    僕は
    0.45
    wget
    0.44
    მასრულ
    0.43
    做得
    0.42
     przetwarz
    0.42
    Activations Density 0.001%

    No Known Activations