© 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. 152902
    Prev
    Next
    INDEX
    Explanations

    Drums Along the Mohawk

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

    value of

    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
    居民
    0.51
    '].
    0.46
    iget
    0.46
    icates
    0.46
    捕
    0.45
    robe
    0.45
    。）
    0.44
    撻
    0.44
    isset
    0.43
    託
    0.43
    POSITIVE LOGITS
     bästa
    0.54
     degré
    0.52
     Yuki
    0.52
     Seh
    0.51
     définitive
    0.50
     suivi
    0.49
     zaz
    0.49
     Menon
    0.48
     Astrid
    0.48
     descrição
    0.48
    Activations Density 0.002%

    No Known Activations