© 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. 82782
    Prev
    Next
    INDEX
    Explanations

    price variants

    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
     spati
    -0.83
     Betting
    -0.78
    ستون
    -0.77
    BIAS
    -0.74
    setLength
    -0.74
    噻
    -0.73
     Attendance
    -0.73
    StatusBar
    -0.71
    ichtliche
    -0.70
    ့
    -0.70
    POSITIVE LOGITS
     variant
    1.15
     prices
    1.09
    variant
    0.99
     price
    0.98
     Variant
    0.97
    Prices
    0.94
     variants
    0.93
    Variant
    0.89
     Prices
    0.86
     bookings
    0.86
    Activations Density 0.012%

    No Known Activations