© 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. 90953
    Prev
    Next
    INDEX
    Explanations

    numbers and names

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

    Lack of clear markings

    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
    Negative Logits
     astonishing
    0.47
     extravag
    0.46
     exif
    0.46
    ും
    0.45
    範
    0.45
    ска
    0.45
    в
    0.44
    囱
    0.44
    是最
    0.43
     auspicious
    0.43
    POSITIVE LOGITS
    arry
    0.48
     допомогою
    0.46
     zmniejs
    0.44
    ffi
    0.43
     ट्रेनों
    0.43
     ফলে
    0.42
    atthena
    0.42
     seguinte
    0.41
    ethy
    0.41
     ہی
    0.41
    Activations Density 0.000%

    No Known Activations