© 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. 14898
    Prev
    Next
    INDEX
    Explanations

    administering medication

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

    The neuron is detecting numeric tokens—numbers and number-like strings (including decimals) in the 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
    0.70
    0
    0.67
    0.61
    2
    0.59
    1
    0.58
    4
    0.56
    3
    0.55
    9
    0.54
    Browser
    0.53
    Datei
    0.52
    POSITIVE LOGITS
     Tjiwarl
    0.70
     Outdoors
    0.64
     surmounted
    0.63
     complemented
    0.61
     Giveaway
    0.60
    iamine
    0.59
     championed
    0.59
     Improving
    0.58
     Yhat
    0.58
     Wail
    0.58
    Activations Density 0.021%

    No Known Activations