© 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. 153294
    Prev
    Next
    INDEX
    Explanations

    A followed by a description

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

    representing lists

    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
     flancs
    0.56
    텐츠
    0.53
    ivad
    0.51
    醌
    0.51
    ït
    0.50
     thereby
    0.48
     facteurs
    0.48
    ००
    0.48
    ്ര
    0.47
     زید
    0.46
    POSITIVE LOGITS
    ಾಗಿತ್ತು
    0.46
    ाना
    0.44
    獨
    0.42
    模擬
    0.42
     abortions
    0.41
    पित
    0.41
    হিত
    0.41
    Human
    0.41
    een
    0.40
    eine
    0.40
    Activations Density 0.008%

    No Known Activations