© 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. 166817
    Prev
    Next
    INDEX
    Explanations

    Internet access provider or IP address

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

    literature, specific terms, concepts

    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
     కార్డు
    0.53
     修改
    0.51
    镕
    0.51
     书
    0.48
     定义
    0.48
     条件
    0.48
     टेक्स्ट
    0.47
     命令
    0.46
    汾
    0.46
    謃
    0.45
    POSITIVE LOGITS
     elev
    0.50
     tetapi
    0.48
     quattro
    0.46
     fakat
    0.45
     efflux
    0.45
     nau
    0.44
     hoi
    0.44
     ilk
    0.44
     anarchy
    0.44
     deport
    0.43
    Activations Density 0.006%

    No Known Activations