© 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. 220860
    Prev
    Next
    INDEX
    Explanations

    extended, fail, finish, feast

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

    reluctant dominant assistant

    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
    Kenya
    0.48
     Chapter
    0.45
    QU
    0.45
     Kenyan
    0.44
     Biographical
    0.43
    t
    0.43
     Practice
    0.42
    ikir
    0.42
     जगत
    0.42
     Copp
    0.42
    POSITIVE LOGITS
     වල
    0.51
    assistant
    0.46
     ಸಾಮ
    0.45
    铃
    0.45
    favorites
    0.45
     inflamed
    0.45
    များ
    0.45
     श्रा
    0.44
    aménagement
    0.44
     élargies
    0.44
    Activations Density 0.000%

    No Known Activations