© 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. 153331
    Prev
    Next
    INDEX
    Explanations

    PHPT, Orioles prospect, SPS

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

    rumbled, have, increased, making, please, we, captured

    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
    ǧ
    0.59
    riminal
    0.50
    सीय
    0.50
    insurer
    0.50
    getLogger
    0.48
    🤮
    0.47
    违反
    0.47
    bilisi
    0.46
    ן
    0.46
    rafpunkte
    0.46
    POSITIVE LOGITS
     dryness
    0.43
     KC
    0.43
     phil
    0.41
    資訊
    0.41
     PHIL
    0.41
     chiefly
    0.41
     xo
    0.41
     Bells
    0.41
     nyní
    0.41
     humidity
    0.40
    Activations Density 0.018%

    No Known Activations