© 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. 178588
    Prev
    Next
    INDEX
    Explanations

    application, excellent, vote, stocking, communication, Foods, last

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

    discretionary income, human gestation, shattering glass

    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
    录
    0.49
    ueve
    0.47
     fairly
    0.46
    otro
    0.45
    ib
    0.45
    ต่าง
    0.45
    indra
    0.44
    |।
    0.44
     완료
    0.44
    CN
    0.44
    POSITIVE LOGITS
     v
    0.48
    V
    0.47
     Conductivity
    0.45
     вершины
    0.44
     glEnable
    0.43
    BarStyle
    0.43
     gonflement
    0.43
    燒
    0.43
     conductivity
    0.42
     Destroy
    0.42
    Activations Density 0.001%

    No Known Activations