© 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. 4697
    Prev
    Next
    INDEX
    Explanations

    EPS file formats

    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
    Negative Logits
    y
    0.80
    en
    0.79
    il
    0.70
    ii
    0.69
    it
    0.66
    (
    0.65
    é
    0.64
    rne
    0.64
    rances
    0.64
     oleh
    0.63
    POSITIVE LOGITS
    EPS
    0.85
    га
    0.82
    д
    0.79
    на
    0.77
     excite
    0.72
    大
    0.72
    PDF
    0.71
    나
    0.71
    он
    0.70
    ну
    0.69
    Activations Density 0.000%

    No Known Activations