© 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. 207834
    Prev
    Next
    INDEX
    Explanations

    legal and financial contexts

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

    evaporation, impedance, images, Sweep

    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
    یر
    0.51
    оз
    0.49
     दिनों
    0.49
    ро
    0.48
    िश
    0.47
    식
    0.47
    trails
    0.46
    تر
    0.46
    n
    0.46
    1
    0.46
    POSITIVE LOGITS
     Standort
    0.50
     Superhero
    0.49
     interdependent
    0.48
     ebben
    0.48
     dBASE
    0.47
     Archae
    0.47
     mathemat
    0.47
     arXiv
    0.47
     Euclidean
    0.47
     Rezept
    0.47
    Activations Density 0.000%

    No Known Activations