© 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. 8105
    Prev
    Next
    INDEX
    Explanations

    code syntax punctuation

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

    The neuron detects references to numeric quantities (including numerals, number words, and decimal values).

    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
     outlying
    0.76
    ncia
    0.71
     defeating
    0.70
     chwili
    0.66
     preprocessing
    0.65
    ໃຈ
    0.64
    冢
    0.64
    ἢ
    0.64
     গভীর
    0.64
     tableaux
    0.64
    POSITIVE LOGITS
    genCode
    0.88
    গি
    0.86
    GEN
    0.79
     Fokker
    0.77
     Collect
    0.75
    För
    0.75
     Kön
    0.74
    весто
    0.74
     término
    0.73
    viat
    0.72
    Activations Density 0.000%

    No Known Activations