© 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. 167936
    Prev
    Next
    INDEX
    Explanations

    enemies, Friday, glory, poor

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

    consists of, curious observer, temporal teleportation

    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
     السيد
    0.51
    勇敢
    0.51
    멋
    0.51
     носи
    0.49
    厉害
    0.49
     تخت
    0.48
     حسين
    0.48
    Trashed
    0.47
    डम
    0.46
    或者
    0.45
    POSITIVE LOGITS
     biomed
    0.45
     Clerk
    0.45
     Farm
    0.44
     tatt
    0.44
    ?
    0.44
     botany
    0.43
     minimal
    0.43
    ierne
    0.42
     Graphic
    0.41
     rates
    0.41
    Activations Density 0.000%

    No Known Activations