© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9690
    Prev
    Next
    INDEX
    Explanations

    commas before specific professions or categories

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

    This neuron detects numeric measurements, i.e. floating‐point and other numerical values inserted into 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
     ecco
    0.61
     &
    0.60
     Süden
    0.60
     arXiv
    0.59
     ImageView
    0.59
     Ph
    0.58
     şi
    0.58
     pharma
    0.58
     kỳ
    0.58
     defineConfig
    0.58
    POSITIVE LOGITS
    provide
    0.67
     सकेंगे
    0.65
     allowances
    0.64
    提供
    0.63
    ఆర్‌
    0.61
    elina
    0.60
    엷
    0.60
    dict
    0.59
    setString
    0.59
    طلاع
    0.59
    Activations Density 0.126%

    No Known Activations