© 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. 56489
    Prev
    Next
    INDEX
    Explanations

    investment, names, links, login

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

    lubricants, security, costs, element

    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
    外
    0.49
     идеи
    0.46
    alumno
    0.44
    社交
    0.44
    鄢
    0.43
     చ
    0.42
    ună
    0.42
    ную
    0.41
     Albums
    0.41
    SOCIAL
    0.41
    POSITIVE LOGITS
     링크
    0.47
    ihanna
    0.46
     slippery
    0.46
    "});
    0.46
    '];?>
    0.45
     투자
    0.45
    จึง
    0.44
     homogenization
    0.43
     vaporization
    0.43
     macroeconomic
    0.42
    Activations Density 0.001%

    No Known Activations