© 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. 170450
    Prev
    Next
    INDEX
    Explanations

    options and conditions

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

    hypotheses and predictions

    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
    d
    0.61
    Animals
    0.50
     Roads
    0.49
    पाक
    0.46
    ιος
    0.46
     Cows
    0.45
    磴
    0.45
    Transforms
    0.45
     Vuitton
    0.45
    Attack
    0.43
    POSITIVE LOGITS
     exacerbated
    0.49
     hypothesized
    0.48
     spiral
    0.46
     оши
    0.46
     також
    0.45
     hypothes
    0.45
     israel
    0.45
    ogloss
    0.45
    lingual
    0.44
    “
    0.44
    Activations Density 0.001%

    No Known Activations