© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 43059
    Prev
    Next
    INDEX
    Explanations

    foreign language characters

    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
    ﻻ
    0.49
     Hawthorne
    0.46
    Jun
    0.45
    '
    0.43
    Haw
    0.43
    <start_of_image>
    0.43
    unknown
    0.42
    cliff
    0.41
    ices
    0.41
    internal
    0.40
    POSITIVE LOGITS
     ମ
    0.53
     vaisse
    0.52
     পরীক্ষার
    0.50
     diffère
    0.49
     dhinak
    0.48
     اجمع
    0.48
     étroite
    0.48
     مریض
    0.47
     કેટલાક
    0.47
    revalidator
    0.47
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.