© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100205
    Prev
    Next
    INDEX
    Explanations

    alcoholic beverages and distilleries

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

    The neuron strongly activates on words naming alcoholic beverages (especially distilled spirits like whiskey, bourbon, vodka, gin, malt, etc.) and related distillation terms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    鑁
    -1.41
     prenant
    -1.38
    signs
    -1.38
     its
    -1.36
    estima
    -1.35
    plans
    -1.31
    commonly
    -1.29
    kreises
    -1.28
    ENIA
    -1.24
    
    -1.24
    POSITIVE LOGITS
    ׇ
    1.28
     forskjellige
    1.25
     should
    1.24
     belligerent
    1.22
    ֺ
    1.18
     noticeably
    1.17
     sırasında
    1.17
    boxylic
    1.16
    Before
    1.16
     what
    1.15
    Activations Density 0.031%

    No Known Activations