© 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. 192931
    Prev
    Next
    INDEX
    Explanations

    drives feature

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

    contrasts and alternatives

    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
    3
    0.57
    anti
    0.54
    prior
    0.53
    by
    0.52
    eg
    0.50
    cal
    0.49
    ig
    0.49
    arrows
    0.49
    bi
    0.49
    partial
    0.48
    POSITIVE LOGITS
     অবস্থার
    0.52
    atsioon
    0.51
    י
    0.49
     анализа
    0.47
     kanske
    0.46
    став
    0.46
    ཇ
    0.45
    昻
    0.45
     Wanda
    0.44
    薀
    0.44
    Activations Density 0.002%

    No Known Activations