© 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. 187076
    Prev
    Next
    INDEX
    Explanations

    common grammatical pairings

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

    threatens to

    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
     driving
    0.46
    Driving
    0.44
     sni
    0.44
    驱
    0.43
     lass
    0.43
     repe
    0.43
     cha
    0.42
     fer
    0.42
    ……
    0.41
    عي
    0.41
    POSITIVE LOGITS
    <unused283>
    0.54
     Неза
    0.50
    MyHomePage
    0.50
    പ്പ
    0.50
     खपत
    0.50
    ದಗ
    0.49
    <unused131>
    0.49
     brunâtre
    0.48
    덮
    0.48
     సంబంధించిన
    0.48
    Activations Density 0.001%

    No Known Activations