© 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. 82869
    Prev
    Next
    INDEX
    Explanations

    political dissertations, high temp cables

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

    Genome Browser Screenshots, dynamic wallpapers

    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
    tariff
    0.50
    ೈನ
    0.47
    несла
    0.46
    Kya
    0.46
    萵
    0.43
    타고
    0.42
     preponder
    0.42
    ಶಸ್
    0.42
    ли
    0.41
    콜
    0.41
    POSITIVE LOGITS
     ብ
    0.51
     Bi
    0.50
     ው
    0.48
    訨
    0.48
    aces
    0.48
     Utah
    0.46
     Fl
    0.46
     ម
    0.46
    ately
    0.45
     Air
    0.44
    Activations Density 0.001%

    No Known Activations