© 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. 87320
    Prev
    Next
    INDEX
    Explanations

    day that

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

    specific word associations

    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
    Not in Any Lists

    No Comments

    Negative Logits
     that
    0.50
    ეგის
    0.47
     বিবেচনায়
    0.43
     slat
    0.42
    that
    0.42
    भे
    0.42
    its
    0.41
    ૅ
    0.40
    using
    0.40
    勝
    0.40
    POSITIVE LOGITS
     çıkar
    0.51
     Hoje
    0.49
    زمانہ
    0.47
     Río
    0.46
     szczególnie
    0.46
     زمانہ
    0.46
     świę
    0.45
     وحده
    0.45
     Peppers
    0.44
     pezzi
    0.44
    Activations Density 0.001%

    No Known Activations