© 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. 229733
    Prev
    Next
    INDEX
    Explanations

    foreign or specific entities

    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
    agar
    0.61
    ana
    0.55
    %
    0.52
    ina
    0.51
    ond
    0.50
    agnetic
    0.50
    %(
    0.49
    olina
    0.49
    ila
    0.48
    arial
    0.47
    POSITIVE LOGITS
     playGame
    0.53
    طبيق
    0.52
     dobr
    0.50
     műkö
    0.49
     larc
    0.48
     nuk
    0.47
    ᓛ
    0.46
     angry
    0.46
     cheery
    0.46
    杭
    0.46
    Activations Density 0.001%

    No Known Activations