© 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. 11987
    Prev
    Next
    INDEX
    Explanations

    registration date column

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

    The neuron strongly activates on floating‐point numeric values (tokens representing decimal 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
    SHOP
    0.82
    0.76
    Essentials
    0.74
    0.71
    0.71
    0.70
     както
    0.67
     کاس
    0.67
    typed
    0.66
    "$
    0.66
    POSITIVE LOGITS
    ل
    0.95
     egyéb
    0.88
    事務所
    0.87
     uniting
    0.83
     nazw
    0.82
     pubblici
    0.82
     rupani
    0.81
    分野
    0.79
    名は
    0.79
    今
    0.79
    Activations Density 0.000%

    No Known Activations