© 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. 211823
    Prev
    Next
    INDEX
    Explanations

    numbers and specific words

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

    whether to adjust

    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
    V
    0.52
    Pr
    0.50
    Categories
    0.50
    Y
    0.49
    Country
    0.48
    Timber
    0.48
    Maz
    0.47
    Missing
    0.47
    Jason
    0.46
    Mag
    0.46
    POSITIVE LOGITS
    usingCamera
    0.51
    <unused42>
    0.50
     વિશે
    0.50
    ни
    0.49
    као
    0.49
     腕時計
    0.48
     ಸ್ನೇಹಿತ
    0.47
    ckså
    0.47
     மன்னி
    0.47
     blushed
    0.47
    Activations Density 0.001%

    No Known Activations