© 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. 24-GEMMASCOPE-2-RES-16K
    7. 15030
    Prev
    Next
    INDEX
    Explanations

    The main thing this neuron does is detect numeric quantity expressions and measurement units (e.g. dosages, volumes, counts).

    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
    🏗
    1.00
     IEEE
    1.00
    レクトリ
    0.99
    тельством
    0.98
     Organizations
    0.97
    🏛
    0.96
    IEEE
    0.96
    financ
    0.96
    veranst
    0.96
    🏟
    0.95
    POSITIVE LOGITS
     ingredients
    1.80
     ointment
    1.80
     probiotic
    1.79
     powders
    1.78
     lotions
    1.77
     ingrédients
    1.76
     tincture
    1.71
     bioactive
    1.70
     lotion
    1.70
     preservatives
    1.70
    Activations Density 1.966%

    No Known Activations