© 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. 15583
    Prev
    Next
    INDEX
    Explanations

    South American camelids

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

    The neuron fires on numerical tokens representing measured or statistical quantities—particularly multi-digit numbers with decimal points.

    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
    0.83
    쨰
    0.75
    卩
    0.75
     Еў
    0.71
    ʝ
    0.71
    sample
    0.69
     అర్
    0.69
    lli
    0.68
    arrison
    0.68
     সাবেক
    0.68
    POSITIVE LOGITS
    Wak
    0.79
    ть
    0.76
    อยาก
    0.76
     bruit
    0.75
    િતા
    0.74
    と思う
    0.73
    驚
    0.72
     天
    0.72
    そうな
    0.71
    嚟
    0.71
    Activations Density 0.001%

    No Known Activations