© 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. 10665
    Prev
    Next
    INDEX
    Explanations

    acquisition and defined

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

    The neuron strongly activates on tokens representing decimal numeric values (floating-point numbers) 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
    м
    0.79
     Grazie
    0.77
     شائع
    0.73
    нняя
    0.71
     batteria
    0.71
    ای
    0.71
     frozen
    0.70
     fetching
    0.70
    ینڈ
    0.70
    ٹ
    0.70
    POSITIVE LOGITS
    dump
    0.82
    addClass
    0.82
     notamment
    0.75
    gore
    0.75
    fm
    0.74
    that
    0.74
    gob
    0.74
    syn
    0.73
    brow
    0.73
    Arthur
    0.73
    Activations Density 0.000%

    No Known Activations