© 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. 12794
    Prev
    Next
    INDEX
    Explanations

    operational promise delimiter that utils robust layout

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

    The neuron is responding to floating‐point numeric tokens (decimal 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
    jším
    0.96
    jších
    0.95
    𝘺
    0.88
    นั้น
    0.83
    ták
    0.83
     Agnes
    0.82
     disertai
    0.82
     léz
    0.81
     upay
    0.79
    𝘭
    0.78
    POSITIVE LOGITS
    Ци
    0.77
     Coh
    0.72
    בור
    0.70
    Rep
    0.70
    Москва
    0.69
    邦
    0.69
    endo
    0.68
    َق
    0.68
     Rep
    0.66
    olute
    0.65
    Activations Density 0.000%

    No Known Activations