© 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. 117866
    Prev
    Next
    INDEX
    Explanations

    Christmas Eve, JFK, customize your

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

    explaining tricky tasks

    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
     není
    0.53
    á
    0.51
    oa
    0.49
    although
    0.47
     sería
    0.47
    жает
    0.46
    o
    0.46
     palabra
    0.45
    ia
    0.45
     dejó
    0.45
    POSITIVE LOGITS
     emulsions
    0.45
     Biomedical
    0.45
     различни
    0.44
     متنوع
    0.44
     Comparisons
    0.44
     biopsies
    0.43
    வில்
    0.43
     emulsion
    0.43
    🫐
    0.43
     comparisons
    0.43
    Activations Density 0.000%

    No Known Activations