© 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. 216133
    Prev
    Next
    INDEX
    Explanations

    diverse language activities

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

    how we perceive or move

    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
    របស់
    0.48
    -
    0.46
     for
    0.45
     Fiberglass
    0.44
     suffering
    0.44
     può
    0.44
    stantially
    0.44
     Zaw
    0.43
    N
    0.43
    n
    0.43
    POSITIVE LOGITS
     অজ্ঞাত
    0.47
    лейбол
    0.47
    大战
    0.46
    ன்ஹீ
    0.45
    狷
    0.44
     शैक्षिक
    0.44
     exceptionnelle
    0.44
    éges
    0.44
    精密
    0.44
    神秘
    0.43
    Activations Density 0.001%

    No Known Activations