© 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. 43536
    Prev
    Next
    INDEX
    Explanations

    college football or basketball

    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_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
     It
    -1.50
     Also
    -1.42
     Furthermore
    -1.38
     Their
    -1.34
     adolescentes
    -1.29
     you
    -1.27
     You
    -1.27
    甴
    -1.26
     Use
    -1.26
     Just
    -1.25
    POSITIVE LOGITS
     帯
    1.59
    Maks
    1.48
    癰
    1.40
     間取り
    1.37
     godk
    1.35
     Bakter
    1.34
    櫺
    1.33
     Koffer
    1.33
     飲
    1.32
    íferos
    1.30
    Activations Density 0.067%

    No Known Activations