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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 98481
    Prev
    Next
    INDEX
    Explanations

    Keith followed by surname

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    パリ
    -0.95
    とある
    -0.94
    特斯拉
    -0.94
    袮
    -0.94
     comparatively
    -0.93
     intensely
    -0.93
     using
    -0.90
     virtue
    -0.90
     efficient
    -0.90
     important
    -0.89
    POSITIVE LOGITS
    ){
    1.19
    Luv
    1.06
     выз
    1.03
    UALA
    0.97
     meest
    0.97
    ));
    0.97
    jük
    0.96
    蜮
    0.96
    THS
    0.96
    телем
    0.96
    Activations Density 0.005%

    No Known Activations