© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 2055
    Prev
    Next
    INDEX
    Explanations

    cloves and garlic

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

    The main thing this neuron does is detect numeric measurements and quantities (numbers often paired with units) in scientific or procedural 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_24_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
    står
    0.72
    imbulkan
    0.71
    瞩
    0.71
    kommt
    0.71
    bygg
    0.70
    Đây
    0.68
    daad
    0.68
    ıyor
    0.67
    贏
    0.66
    ancien
    0.66
    POSITIVE LOGITS
     aqueous
    1.07
     sodium
    1.06
     sucrose
    1.01
     preferably
    0.99
     polystyrene
    0.99
     polyvinyl
    0.98
     teaspoon
    0.98
     polyethylene
    0.96
     tablespoon
    0.96
     pectin
    0.96
    Activations Density 0.096%

    No Known Activations