© 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. 246888
    Prev
    Next
    INDEX
    Explanations

    foreign language or locale

    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
    Alexandra
    0.51
    Pierre
    0.49
    자
    0.48
    āju
    0.46
    Jason
    0.46
     jambes
    0.46
    Category
    0.45
     thrombo
    0.45
    К
    0.45
    Lights
    0.44
    POSITIVE LOGITS
     Reforms
    0.48
     現
    0.45
     эсте
    0.45
     ಏಕೆ
    0.44
     Reform
    0.44
     अनावश्यक
    0.44
    anaan
    0.44
     Election
    0.43
    lesia
    0.43
     любые
    0.41
    Activations Density 0.000%

    No Known Activations