© 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. 141184
    Prev
    Next
    INDEX
    Explanations

    country using

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

    breaches, problems, checkpoints, hole

    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
     atténuées
    0.59
     அம்ச
    0.59
     нередко
    0.50
     ошибки
    0.49
    ológica
    0.49
     éléments
    0.48
    👄
    0.48
     ادارے
    0.48
     школе
    0.48
     ошибка
    0.48
    POSITIVE LOGITS
    a
    0.61
    on
    0.57
    inin
    0.57
    7
    0.53
     success
    0.52
    ith
    0.51
    ani
    0.51
    F
    0.50
    e
    0.50
    ined
    0.50
    Activations Density 0.001%

    No Known Activations