© 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. 34-GEMMASCOPE-RES-131K
    7. 59455
    Prev
    Next
    INDEX
    Explanations

    hiking boots

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is specialized to pick up technical product‐specification language—brand/model names, features, measurements, and other spec details in a product review.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     Kalman
    -0.83
    optimizer
    -0.72
     enseña
    -0.70
    Roberts
    -0.69
     Pist
    -0.69
     rockets
    -0.68
    entiation
    -0.68
    芥
    -0.68
     문
    -0.68
    atov
    -0.68
    POSITIVE LOGITS
     hiking
    1.02
     hikers
    0.86
     waterproof
    0.86
    ಿದೆ
    0.86
     támogat
    0.84
     trail
    0.83
     hikes
    0.82
     SUPPORT
    0.79
     amphibi
    0.79
     backpacking
    0.77
    Activations Density 0.009%

    No Known Activations