© 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. 117906
    Prev
    Next
    INDEX
    Explanations

    delivery, waste, reported, shakes, butter

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

    compound word starters

    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
     встречи
    0.46
    .`);
    0.46
    讨厌
    0.44
     amoureux
    0.44
     yıldır
    0.43
     tolerancia
    0.42
    农民
    0.42
    vrir
    0.41
     believers
    0.40
     hateful
    0.40
    POSITIVE LOGITS
     then
    0.47
     another
    0.47
    another
    0.44
     Paddington
    0.43
    د
    0.42
    access
    0.42
     products
    0.42
     Cavendish
    0.41
    systems
    0.41
     Dign
    0.41
    Activations Density 0.000%

    No Known Activations