© 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. 75657
    Prev
    Next
    INDEX
    Explanations

    application, began, just, listings, styles, below

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

    "all but", "almost"

    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
     পৌঁছ
    0.44
     অবদান
    0.43
    료
    0.41
    嶈
    0.40
    مرات
    0.39
    饴
    0.39
     residing
    0.38
     coolant
    0.38
     aromas
    0.38
    沿
    0.37
    POSITIVE LOGITS
     Netz
    0.47
    deals
    0.47
     снаб
    0.46
    s
    0.46
    гій
    0.45
    und
    0.45
    ugia
    0.45
    gid
    0.44
    das
    0.44
    gyz
    0.44
    Activations Density 0.000%

    No Known Activations