© 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. 129599
    Prev
    Next
    INDEX
    Explanations

    setup, reminder, remains, inches, logo, range

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

    url and chat

    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
    青春
    0.47
    alah
    0.44
    店
    0.43
    rules
    0.43
    arb
    0.42
    itamos
    0.42
    ueil
    0.42
    ecs
    0.41
    丽
    0.41
    norms
    0.41
    POSITIVE LOGITS
     Gabriella
    0.47
    डेट
    0.45
     ዓይነት
    0.44
     unión
    0.44
    ‒
    0.43
     приве
    0.41
     importation
    0.41
     phishing
    0.41
     impervious
    0.41
     रहेंगी
    0.41
    Activations Density 0.001%

    No Known Activations