© 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. 90258
    Prev
    Next
    INDEX
    Explanations

    blind judging entries

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

    The neuron selectively fires on wine‐review jargon—especially varietal names (like “Riesling” or “Welschriesling”) and tasting/judging terms (e.g. “tasting,” “blind,” “category”).

    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
    rep
    -0.83
    mu
    -0.82
    ball
    -0.72
    sim
    -0.72
    雛
    -0.71
    bata
    -0.71
    nom
    -0.71
    體
    -0.70
    ......
    -0.70
    gamma
    -0.70
    POSITIVE LOGITS
     blind
    1.33
    blind
    1.14
    Blind
    1.04
     Blind
    1.02
     entrants
    0.97
     blindly
    0.96
     entries
    0.94
     judging
    0.92
     competitions
    0.90
     Entries
    0.90
    Activations Density 0.008%

    No Known Activations