© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102973
    Prev
    Next
    INDEX
    Explanations

    github.io

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

    the ".io" domain extension in URLs, particularly in GitHub Pages and documentation links.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     in
    -2.23
     Using
    -2.22
     ,
    -2.13
    $,
    -2.13
    ,
    -2.06
     However
    -2.06
     out
    -2.02
     after
    -1.99
     Without
    -1.98
     Some
    -1.97
    POSITIVE LOGITS
     素描
    2.23
     abiye
    2.19
     收納
    2.19
     チラ
    2.13
     花纹
    2.11
     起毛
    2.06
    搋
    2.05
     実例
    2.02
     dezelve
    2.00
     剧照
    1.98
    Activations Density 0.001%

    No Known Activations