© 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. 110757
    Prev
    Next
    INDEX
    Explanations

    teams playing each other

    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
     semifinal
    -1.02
    Semif
    -0.85
     new
    -0.82
     semifinals
    -0.82
    laud
    -0.79
     finals
    -0.78
     undangan
    -0.75
    Urls
    -0.75
     semi
    -0.74
     stø
    -0.73
    POSITIVE LOGITS
     mindig
    0.81
    geschenk
    0.81
    Interested
    0.77
     volup
    0.77
     }^{(
    0.75
    asible
    0.75
    directly
    0.73
     quà
    0.71
    interested
    0.71
    orthand
    0.71
    Activations Density 0.013%

    No Known Activations