© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 200240
    Prev
    Next
    INDEX
    Explanations

    fall, especially, roll

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    esque
    0.53
    ב
    0.53
     used
    0.48
    وای
    0.47
    ed
    0.47
    מית
    0.46
     could
    0.46
    データ
    0.46
    This
    0.46
    к
    0.46
    POSITIVE LOGITS
     ElevatedButton
    0.50
     녹
    0.48
     trồng
    0.46
     नोंद
    0.46
     المت
    0.45
    🧼
    0.45
    PathDirectory
    0.45
     عش
    0.44
    attup
    0.44
     күн
    0.44
    Activations Density 0.001%

    No Known Activations