© 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. 166684
    Prev
    Next
    INDEX
    Explanations

    assigned to

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

    powered extension

    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
    so
    0.44
    ER
    0.43
    жде
    0.43
    er
    0.43
    site
    0.43
    test
    0.43
    ادی
    0.43
    see
    0.42
    ｅ
    0.42
    t
    0.40
    POSITIVE LOGITS
    buttonclick
    0.50
     réalisée
    0.50
     осигурање
    0.49
     दिरहम
    0.48
    臆
    0.47
    审查
    0.46
     सहज
    0.46
    écran
    0.46
     स्क्रीनिंग
    0.45
     ശരീര
    0.45
    Activations Density 0.001%

    No Known Activations