© 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. 141223
    Prev
    Next
    INDEX
    Explanations

    multilingual and specific phrasing

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

    Anything exciting or interesting

    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
    /
    0.52
    +
    0.50
    %
    0.50
     ALL
    0.49
     BUT
    0.49
     Archer
    0.49
     Oracle
    0.48
    =
    0.48
     *
    0.46
     Higgins
    0.46
    POSITIVE LOGITS
    сум
    0.50
    輸入
    0.46
    實際
    0.46
    
    0.45
     विनम्र
    0.44
     విశ
    0.44
     прось
    0.44
    ឹក
    0.44
    espèces
    0.43
     वास्तव
    0.42
    Activations Density 0.001%

    No Known Activations