© 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. 22-GEMMASCOPE-RES-131K
    7. 130546
    Prev
    Next
    INDEX
    Explanations

    sports and relationships

    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_22/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
     vivimos
    -0.98
     endures
    -0.88
     comerciales
    -0.85
     aún
    -0.85
     mercancías
    -0.82
     administrativa
    -0.82
    :}
    -0.80
    farande
    -0.79
     críticos
    -0.79
    andoah
    -0.78
    POSITIVE LOGITS
     अपनी
    0.94
    offer
    0.90
    simple
    0.83
     arXiv
    0.82
    nery
    0.81
    hores
    0.81
    Offer
    0.81
    tét
    0.79
    offered
    0.78
    šia
    0.77
    Activations Density 0.055%

    No Known Activations