© 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. 171913
    Prev
    Next
    INDEX
    Explanations

    Stella mentioning the God

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

    spherical, actively, say "

    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
     ያላቸው
    0.55
     ustedes
    0.52
     ಬಳಕೆ
    0.51
     puissent
    0.51
     वंचित
    0.50
    婭
    0.49
    ವರೆ
    0.47
     tengan
    0.46
     Ugandan
    0.46
     вас
    0.46
    POSITIVE LOGITS
    Examples
    0.54
    f
    0.51
     onDelete
    0.50
    ло
    0.50
    격
    0.50
    lr
    0.49
    ロ
    0.49
    ron
    0.48
    런
    0.48
    FR
    0.47
    Activations Density 0.000%

    No Known Activations