© 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. 77892
    Prev
    Next
    INDEX
    Explanations

    native language, surpasses Baby

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

    asking questions

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Dixit
    0.53
     judicious
    0.51
     sweetness
    0.46
     incessant
    0.44
     Pob
    0.44
     Piso
    0.43
     wondrous
    0.43
    窘
    0.43
     viciss
    0.43
     triumphant
    0.42
    POSITIVE LOGITS
     оско
    0.43
     превы
    0.43
    %"
    0.42
    '
    0.42
     الله
    0.41
     brachte
    0.41
     *"
    0.41
     тормо
    0.40
     filmu
    0.40
     fratern
    0.40
    Activations Density 0.000%

    No Known Activations