© 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. 198657
    Prev
    Next
    INDEX
    Explanations

    taking pictureswould reactperfect boundMobile Bankingsilver GIRTH

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

    understanding how to debug

    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
    स
    0.51
    高兴
    0.46
    س
    0.46
     serialize
    0.44
    Waters
    0.44
    S
    0.44
    ส
    0.44
     koniec
    0.43
    হ
    0.43
     estabele
    0.43
    POSITIVE LOGITS
     Bakufu
    0.50
     CURLE
    0.46
     Bridal
    0.46
    cích
    0.46
     EMPC
    0.45
    馅
    0.45
    alles
    0.44
    ongiorno
    0.44
    idavit
    0.43
     Flächen
    0.43
    Activations Density 0.000%

    No Known Activations