© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 5486
    Prev
    Next
    INDEX
    Explanations

    das

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

    The neuron is strongly activated by numeric tokens—especially floating‐point numbers (e.g. measurements or statistics 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
    黍
    0.78
    ণিজ
    0.75
    меры
    0.74
     vuccati
    0.73
    пут
    0.73
    бычно
    0.73
    paging
    0.73
     vadati
    0.73
     основные
    0.72
     selfless
    0.72
    POSITIVE LOGITS
    ال
    0.78
     م
    0.75
     josé
    0.73
     smtp
    0.72
     فا
    0.71
     Ciudad
    0.71
     pw
    0.70
     bol
    0.70
     rp
    0.69
    enture
    0.69
    Activations Density 0.002%

    No Known Activations