© 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. 173957
    Prev
    Next
    INDEX
    Explanations

    word sequences

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

    natural versus awkward phrasing

    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
    う
    0.56
    深刻
    0.47
    人用
    0.46
    茘
    0.46
    ぐるみ
    0.46
    だけで
    0.45
    会議
    0.44
     う
    0.43
    外国
    0.43
    ધ
    0.43
    POSITIVE LOGITS
     compositional
    0.51
     schematic
    0.50
     interchangeable
    0.50
     pudd
    0.49
     drywall
    0.49
     impending
    0.48
     skincare
    0.48
     textural
    0.48
     punctuation
    0.48
     stylistic
    0.48
    Activations Density 0.002%

    No Known Activations