© 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. 217790
    Prev
    Next
    INDEX
    Explanations

    statistical processing and corporate income

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

    merger

    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
     Kershaw
    0.48
     ప్రస్తుతం
    0.47
    ndham
    0.45
     Hwy
    0.45
    ষা
    0.44
     spectators
    0.44
     ఘ
    0.43
     Slab
    0.43
    woorden
    0.42
    പ
    0.42
    POSITIVE LOGITS
    についての
    0.48
     aritm
    0.48
     vieja
    0.45
     longitudine
    0.45
    hyst
    0.45
    力度
    0.44
    Droite
    0.44
     maladies
    0.43
    hame
    0.42
    を使
    0.42
    Activations Density 0.001%

    No Known Activations