© 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. 192367
    Prev
    Next
    INDEX
    Explanations

    the + specific noun

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

    , for testing, for satire, for creativity

    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
    𝐫
    0.52
    hit
    0.49
    لي
    0.47
    날
    0.46
    갬
    0.44
    pol
    0.44
    ис
    0.44
    кратно
    0.44
    সার
    0.44
    osť
    0.44
    POSITIVE LOGITS
     Sonu
    0.48
    ActionMode
    0.46
    ￠
    0.44
     Auer
    0.43
     ×
    0.42
    Officers
    0.42
     ApJ
    0.42
    Benzyloxy
    0.42
    VisualStudio
    0.42
     Джа
    0.42
    Activations Density 0.000%

    No Known Activations