© 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. 246879
    Prev
    Next
    INDEX
    Explanations

    "quality", "Avast", "powerful", "consistently", "New"

    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
     طریقے
    0.53
     توی
    0.49
    州的
    0.48
     Stimmung
    0.46
    塹
    0.45
     왜
    0.43
     Healing
    0.43
    の値
    0.43
     요
    0.43
    Linked
    0.43
    POSITIVE LOGITS
    avion
    0.47
     przew
    0.45
     econometric
    0.45
     peel
    0.45
     féidir
    0.44
    ΡΟ
    0.44
    substack
    0.43
     echocardi
    0.43
     philipp
    0.43
     बृहस्पतिवार
    0.42
    Activations Density 0.002%

    No Known Activations