© 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. 235414
    Prev
    Next
    INDEX
    Explanations

    classified information

    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
    饼
    0.49
     bạn
    0.48
    跄
    0.48
     próp
    0.48
     proteína
    0.47
    一个人
    0.46
    eleng
    0.46
     аласыз
    0.46
     Bạn
    0.46
    镭
    0.46
    POSITIVE LOGITS
     classified
    0.57
     rendezvous
    0.53
     refuge
    0.50
     classifying
    0.50
     theory
    0.47
     renovation
    0.46
     trial
    0.45
     steam
    0.45
     clasific
    0.45
     theorist
    0.45
    Activations Density 0.000%

    No Known Activations