© 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. 11358
    Prev
    Next
    INDEX
    Explanations

    cooking liquids

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

    The neuron fires strongly on recipe‐style cooking instructions—steps that list ingredients, measurements, and imperative cooking actions.

    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
     चॉकलेट
    0.87
     chocolate
    0.86
     chocolates
    0.82
     шокола
    0.81
    巧克力
    0.79
    チョコレート
    0.79
     chocolat
    0.77
    🍫
    0.77
     Chocol
    0.76
    🍩
    0.74
    POSITIVE LOGITS
     soup
    2.13
    soup
    1.94
     Soup
    1.92
     soups
    1.84
    Soup
    1.67
     boiling
    1.58
    スープ
    1.52
    汤
    1.51
    끓
    1.45
     broth
    1.43
    Activations Density 0.415%

    No Known Activations