© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 35620
    Prev
    Next
    INDEX
    Explanations

    all followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    들이
    0.81
    ຫ
    0.73
    숍
    0.71
    ምት
    0.70
    Т
    0.69
    води
    0.66
    ທີ່
    0.66
    морфи
    0.66
    젬
    0.65
    ТИ
    0.65
    POSITIVE LOGITS
     in
    1.05
    um
    0.91
     was
    0.87
    ng
    0.87
     will
    0.86
     be
    0.85
    de
    0.83
     ,
    0.79
     been
    0.78
    ৮
    0.78
    Activations Density 0.002%

    No Known Activations