© 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. 108141
    Prev
    Next
    INDEX
    Explanations

    between currencies, time, or distances

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

    betweenness or intervals

    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
    认为
    0.57
    認為
    0.49
    极大
    0.46
    ဟာ
    0.44
    招标
    0.44
    机关
    0.44
    疫
    0.43
    艰
    0.43
    疑问
    0.42
     ملین
    0.42
    POSITIVE LOGITS
     zwischen
    0.50
     अंतराल
    0.48
     seper
    0.47
     antara
    0.44
     Anschließend
    0.44
    periodic
    0.44
     kz
    0.44
     between
    0.43
     Zwischen
    0.43
    ระหว่าง
    0.42
    Activations Density 0.000%

    No Known Activations