© 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. 38147
    Prev
    Next
    INDEX
    Explanations

    Gordon Ramsay's Hell's Kitchen

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

    The neuron fires on numeric tokens—digits, version numbers, years, and other number‐like sequences.

    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
     factura
    -0.76
     saveur
    -0.72
     instig
    -0.71
     dryer
    -0.71
     drier
    -0.70
    Discussions
    -0.68
     should
    -0.68
     porch
    -0.68
    夏季
    -0.67
    Tanto
    -0.67
    POSITIVE LOGITS
     Gordon
    0.99
    Hell
    0.98
    Gordon
    0.98
     Hell
    0.96
     HELL
    0.87
     Ramsay
    0.87
     Maze
    0.84
    rams
    0.82
    efits
    0.82
    Rams
    0.80
    Activations Density 0.010%

    No Known Activations