© 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. 141520
    Prev
    Next
    INDEX
    Explanations

    numbers and categories

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

    engineering, formatting, improvements

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Instead
    0.48
    instead
    0.46
     instead
    0.45
    ’
    0.44
    Intensity
    0.44
    using
    0.43
     intensity
    0.43
    intensity
    0.43
     favorites
    0.43
     collim
    0.42
    POSITIVE LOGITS
     ዋና
    0.54
     ресу
    0.48
    URNIZOR
    0.47
     श्रीलंका
    0.47
     πρώτη
    0.47
    ঘাতে
    0.46
     டை
    0.46
     ด่า
    0.45
    砣
    0.45
    aną
    0.45
    Activations Density 0.000%

    No Known Activations