© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 6889
    Prev
    Next
    INDEX
    Explanations

    cycling road races

    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
    プレイヤー
    -0.91
     Schub
    -0.89
    sibile
    -0.89
     demografica
    -0.89
    祂
    -0.89
    𝒫
    -0.87
    Normdaten
    -0.84
     condado
    -0.83
    ispiel
    -0.83
     参数
    -0.83
    POSITIVE LOGITS
     UCI
    1.71
    UCI
    1.35
     race
    1.33
     riders
    1.26
     cycling
    1.26
    vistar
    1.25
     Cycling
    1.23
     cyclists
    1.19
     Shimano
    1.17
     Specialized
    1.16
    Activations Density 0.055%

    No Known Activations