© 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. 186873
    Prev
    Next
    INDEX
    Explanations

    own

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

    exploitation and potential harm

    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
    Negative Logits
    ек
    0.46
    बिट
    0.44
    甛
    0.43
    さんも
    0.41
    фек
    0.41
    साम
    0.40
    люб
    0.40
     socialism
    0.40
    рито
    0.39
    摻
    0.39
    POSITIVE LOGITS
     plausible
    0.47
     plaus
    0.47
    underland
    0.44
     Gegner
    0.42
     lone
    0.41
     morphological
    0.41
    Prediction
    0.41
     alone
    0.40
     hypot
    0.40
     giỏi
    0.40
    Activations Density 0.004%

    No Known Activations