© 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. 56634
    Prev
    Next
    INDEX
    Explanations

    words between concepts

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

    descriptive follow-ups

    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
    ēl
    0.55
    ժ
    0.49
    屇
    0.48
    xcschemes
    0.47
    IRT
    0.47
    šem
    0.46
    Films
    0.46
    walten
    0.46
    漯
    0.46
    Layers
    0.46
    POSITIVE LOGITS
     aggreg
    0.52
     ASCII
    0.51
     declarative
    0.51
     conviction
    0.50
     optimisation
    0.49
     artisanal
    0.49
    ვნ
    0.48
     argu
    0.48
     consistent
    0.48
     rotund
    0.48
    Activations Density 0.000%

    No Known Activations