© 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. 193025
    Prev
    Next
    INDEX
    Explanations

    all donors

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

    precise consensual online tuples

    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
     زندگی
    0.57
     ό
    0.55
     दु
    0.52
     nghĩ
    0.51
     می‌دهد
    0.51
     ζωή
    0.50
     ஒருவர்
    0.50
     삶
    0.50
     खड़े
    0.49
     hypothesized
    0.49
    POSITIVE LOGITS
     capt
    0.48
     Sion
    0.47
     Marlon
    0.47
     pram
    0.46
    IVOS
    0.46
     spoon
    0.45
    কাল
    0.45
     Zeppelin
    0.45
     Aren
    0.44
     Spoon
    0.44
    Activations Density 0.000%

    No Known Activations