© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 13711
    Prev
    Next
    INDEX
    Explanations

    correct grammar

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

    The neuron fires on numeric specifications—i.e. tokens that represent measurement values, quantities, or other numbers.

    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
    𝗣
    0.59
    atributos
    0.58
    ר
    0.57
    ablo
    0.57
    റേ
    0.55
    ರಿಸಿ
    0.55
    ellum
    0.55
     ও
    0.54
    igenza
    0.54
    はもちろん
    0.53
    POSITIVE LOGITS
    ৷
    0.66
     început
    0.63
    ।)
    0.58
     tomonidan
    0.57
     Hau
    0.56
     tarafından
    0.56
    市長
    0.56
    ।"
    0.55
     semoga
    0.55
    めでとう
    0.55
    Activations Density 0.337%

    No Known Activations