© 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. 226527
    Prev
    Next
    INDEX
    Explanations

    methodology early, reporter by, rain or

    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
    ום
    0.49
     увеличи
    0.48
     комментария
    0.48
     कमाई
    0.47
    𝚇
    0.47
    兟
    0.47
     insanely
    0.46
     MINUTES
    0.46
    選挙
    0.46
    ఎస్
    0.46
    POSITIVE LOGITS
     \
    0.61
     l
    0.51
    term
    0.51
    Action
    0.50
    JSON
    0.49
    l
    0.49
    request
    0.47
     adı
    0.47
     Förder
    0.47
     claim
    0.46
    Activations Density 0.002%

    No Known Activations