© 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. 144448
    Prev
    Next
    INDEX
    Explanations

    legal or property rights

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

    witness data

    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
    arna
    0.48
     il
    0.47
     ambul
    0.46
     a
    0.45
     immunology
    0.45
     aula
    0.45
    ili
    0.44
     Current
    0.44
     porta
    0.44
     biolog
    0.44
    POSITIVE LOGITS
    ८
    0.52
     kilomètres
    0.50
    連合
    0.50
     विश्लेषण
    0.50
    ქვენ
    0.50
    ၇
    0.48
    πάρχ
    0.48
     Фургал
    0.48
    時に
    0.46
    變
    0.46
    Activations Density 0.000%

    No Known Activations