© 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. 171961
    Prev
    Next
    INDEX
    Explanations

    developing, marketplace, speaking, current

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

    blinking, fear, star, plants, volume

    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
     HANDLING
    0.54
    πτωση
    0.50
    ೃ
    0.50
    strMeal
    0.49
    Ꮸ
    0.46
     calorimetric
    0.46
    GRANT
    0.45
    ភ្ល
    0.45
     paramagnetic
    0.44
    ﺏ
    0.44
    POSITIVE LOGITS
    an
    0.55
     an
    0.50
    en
    0.50
    Area
    0.48
    ino
    0.47
     مزد
    0.47
    offset
    0.46
    ate
    0.46
     The
    0.46
    area
    0.45
    Activations Density 0.001%

    No Known Activations