© 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. 15646
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

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

    This neuron detects mentions of something being “available on site.”

    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
    e
    0.86
    al
    0.86
    PB
    0.82
    en
    0.81
    etas
    0.79
    hard
    0.77
    Russ
    0.77
    I
    0.77
    el
    0.73
    لع
    0.72
    POSITIVE LOGITS
    وپ
    0.85
     cylind
    0.84
     TextBox
    0.80
     -->'
    0.80
    קי
    0.79
     optimizer
    0.77
    िंट
    0.77
    ере
    0.75
     dupatta
    0.75
     divisão
    0.75
    Activations Density 0.000%

    No Known Activations