© 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. 34-GEMMASCOPE-RES-131K
    7. 109578
    Prev
    Next
    INDEX
    Explanations

    places and sports arenas

    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
    $
    -0.72
    claimer
    -0.71
     studenti
    -0.70
    밭
    -0.70
    "})
    -0.68
    圓
    -0.67
    باب
    -0.66
     entretenimiento
    -0.66
     husqvarna
    -0.66
    ágot
    -0.65
    POSITIVE LOGITS
     arena
    0.93
     arenas
    0.86
     curling
    0.85
    OSHA
    0.78
    arena
    0.78
    itope
    0.77
     outlets
    0.77
     care
    0.75
     (#
    0.74
     находятся
    0.73
    Activations Density 0.038%

    No Known Activations