© 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. 108224
    Prev
    Next
    INDEX
    Explanations

    couples, guests, free

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

    code blocks or structured lists

    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
     لیست
    0.53
    在这里
    0.52
     اینجا
    0.50
    枻
    0.49
     ماشین
    0.49
     ここ
    0.47
    핀
    0.47
    پور
    0.47
    ὐ
    0.47
     هنا
    0.46
    POSITIVE LOGITS
    ¿
    0.57
     for
    0.51
     odp
    0.51
    /
    0.50
     over
    0.49
    ak
    0.48
    ?
    0.47
     catast
    0.46
     campaigners
    0.45
     :
    0.44
    Activations Density 0.000%

    No Known Activations