© 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. 187268
    Prev
    Next
    INDEX
    Explanations

    celebrity names and games

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

    game promised

    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
    hormat
    0.50
     Wiss
    0.50
    ³.
    0.48
    +.
    0.48
    μ
    0.47
    덴
    0.47
    raim
    0.47
    Tax
    0.46
    ي
    0.45
    teilung
    0.45
    POSITIVE LOGITS
     moest
    0.48
     kife
    0.46
     fizeram
    0.45
     hadden
    0.44
     realizaron
    0.44
     klas
    0.43
     forl
    0.43
     ใคร
    0.43
     přek
    0.42
     mujeres
    0.42
    Activations Density 0.001%

    No Known Activations