© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93367
    Prev
    Next
    INDEX
    Explanations

    search queries and filters

    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
    MessageTagHelper
    -0.88
     გ
    -0.88
     frutas
    -0.86
    prek
    -0.86
    otherapy
    -0.85
    过头
    -0.83
     kirim
    -0.82
     uvas
    -0.82
    Sku
    -0.81
    ͣ
    -0.81
    POSITIVE LOGITS
     query
    0.93
    查询
    0.89
     filter
    0.88
     search
    0.88
    ジュー
    0.83
    گي
    0.80
     filtr
    0.80
     select
    0.79
     queries
    0.79
     Limit
    0.78
    Activations Density 0.003%

    No Known Activations