© 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. 67914
    Prev
    Next
    INDEX
    Explanations

    rules of the road or RNA molecules

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

    Linux, Thorne, Wizard, Feature

    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
     appeared
    0.44
     <
    0.44
     п
    0.43
    к
    0.42
     buil
    0.41
    शियों
    0.41
    >=
    0.40
     www
    0.39
     iron
    0.39
     const
    0.39
    POSITIVE LOGITS
    恫
    0.55
    ඖ
    0.51
     यात्री
    0.50
     posteriores
    0.48
     jedem
    0.48
     povez
    0.47
     Zusätzlich
    0.46
    的技术
    0.46
    赐
    0.46
     rada
    0.46
    Activations Density 0.000%

    No Known Activations