© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8715
    Prev
    Next
    INDEX
    Explanations

    plant or fruit cultivation

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

    The neuron strongly activates on wine‐related descriptive passages—labels, producer names, vineyard and cellar details, and tasting‐note style text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     মাছ
    0.68
     Bahamas
    0.62
     kesan
    0.62
    эта
    0.62
     लालू
    0.59
     മത്സ്യ
    0.59
    🍛
    0.59
     эта
    0.58
     собе
    0.58
     பாலை
    0.57
    POSITIVE LOGITS
     grapes
    1.52
     vineyard
    1.51
     grape
    1.38
     vineyards
    1.38
     winemaker
    1.25
    葡萄
    1.20
    grapes
    1.20
     winery
    1.18
    🍇
    1.16
     vines
    1.10
    Activations Density 0.366%

    No Known Activations