© 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. 11390
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on the first content word of a new sentence or list item (e.g. tokens immediately following a period + number or other sentence boundary).

    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
     povez
    0.74
    nica
    0.74
     Balashov
    0.69
     sfr
    0.68
    挿
    0.68
     Liza
    0.67
     Kxf
    0.66
     italic
    0.66
     హైద
    0.64
    鍦
    0.64
    POSITIVE LOGITS
    ل
    0.78
    APER
    0.71
    Algun
    0.68
    谩
    0.68
    ാരോഗ്യ
    0.67
    ONLY
    0.66
    🐋
    0.66
    ck
    0.66
    cimiento
    0.66
    cht
    0.66
    Activations Density 0.000%

    No Known Activations