© 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. 118155
    Prev
    Next
    INDEX
    Explanations

    phrases following punctuation

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

    common word collocations

    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
    ido
    0.53
     sets
    0.45
    ่าว
    0.44
     gulf
    0.43
     Shift
    0.43
     separation
    0.43
    {"
    0.42
    izers
    0.42
    ized
    0.41
     y
    0.41
    POSITIVE LOGITS
    ‌است
    0.52
     PARTIC
    0.52
     efficaces
    0.52
    ರುತ್ತವೆ
    0.50
    BURN
    0.48
     OXIDES
    0.48
    इनस
    0.47
    effic
    0.46
    जेस्टिव
    0.46
     लड़ने
    0.46
    Activations Density 0.001%

    No Known Activations