© 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. 239856
    Prev
    Next
    INDEX
    Explanations

    cancellation requests

    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
    വ്ര
    0.46
     пі
    0.45
    creating
    0.45
     तलाश
    0.45
    seeking
    0.42
    trade
    0.42
    ค้า
    0.40
    ӳ
    0.40
    sale
    0.40
    esk
    0.39
    POSITIVE LOGITS
     vidéo
    0.50
     topik
    0.49
     Comptes
    0.46
     YouTuber
    0.46
     videolar
    0.44
     Batterie
    0.44
     MacBook
    0.42
    പ്പോഴ
    0.42
     शिवम
    0.42
     ২০২২
    0.42
    Activations Density 0.000%

    No Known Activations