© 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. 12946
    Prev
    Next
    INDEX
    Explanations

    writing after time words

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

    The neuron fires strongly on numeric tokens containing decimal points (floating‐point 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
    ቝ
    0.95
    మ్యాచ్
    0.93
     lluv
    0.92
     даль
    0.92
     Biraz
    0.91
     Juegos
    0.89
     новая
    0.89
    ңү
    0.86
    returnValues
    0.86
    paragus
    0.86
    POSITIVE LOGITS
    ت
    0.95
    ified
    0.89
    ed
    0.89
    ors
    0.88
    ف
    0.88
    ado
    0.86
    ell
    0.85
    it
    0.83
     are
    0.83
    لا
    0.82
    Activations Density 0.000%

    No Known Activations