© 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. 145258
    Prev
    Next
    INDEX
    Explanations

    there

    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
     of
    0.71
     -
    0.68
     de
    0.66
     a
    0.63
    د
    0.62
    ə
    0.61
     &
    0.60
     to
    0.59
     pumps
    0.59
     qui
    0.58
    POSITIVE LOGITS
    oil
    0.64
    hereinafter
    0.61
    at
    0.60
     ఆదాయ
    0.59
     ನಡುವ
    0.59
    sites
    0.56
     ಜನರು
    0.55
     নিশ্চিত
    0.55
     ಖರೀ
    0.54
     ಕೈ
    0.54
    Activations Density 0.007%

    No Known Activations