© 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. 81566
    Prev
    Next
    INDEX
    Explanations

    Soviet prisoners, Q:, Journal of

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

    The neuron fires strongly on descriptive tasting‐note language in wine reviews—that is, sensory adjectives and flavor/aroma descriptors (color, aroma, palate, finish, etc.).

    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
    麪
    -0.88
    roberto
    -0.88
     xrange
    -0.87
    😜
    -0.87
    Läh
    -0.84
    דה
    -0.82
    jorge
    -0.81
     彩
    -0.80
    راهن
    -0.80
    POLY
    -0.80
    POSITIVE LOGITS
     deployed
    0.90
    Ф
    0.88
     lacks
    0.81
     購入
    0.80
     дата
    0.79
    issants
    0.78
     hitherto
    0.78
     still
    0.78
    成功
    0.77
     hypnosis
    0.77
    Activations Density 0.008%

    No Known Activations