© 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. 226888
    Prev
    Next
    INDEX
    Explanations

    upload, personalized, product

    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
     landowners
    0.49
    त
    0.47
    owners
    0.46
    ARMA
    0.45
     thảo
    0.43
    زمان
    0.43
     Bunker
    0.42
     vâ
    0.42
    IAB
    0.42
     प्रतिभागियों
    0.42
    POSITIVE LOGITS
     giorno
    0.52
     día
    0.49
     günü
    0.48
    🚄
    0.48
    뚠
    0.46
     später
    0.45
     도입
    0.43
    🚿
    0.43
     relay
    0.42
    TIMESTAMP
    0.42
    Activations Density 0.002%

    No Known Activations