© 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. 13712
    Prev
    Next
    INDEX
    Explanations

    transport groups

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

    This neuron fires on numbered legal-style references (e.g. patent claim 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
    th
    0.95
     with
    0.85
     返
    0.77
    s
    0.77
    ter
    0.75
     farther
    0.75
    不過
    0.74
     với
    0.73
    pushButton
    0.73
    อย่างไร
    0.72
    POSITIVE LOGITS
     गाना
    0.88
    áticos
    0.82
     monolayers
    0.82
     बल्लेबाजी
    0.78
     nomads
    0.77
    ográficos
    0.76
     बल्ले
    0.73
    ু
    0.73
     rayos
    0.72
    ا
    0.72
    Activations Density 0.001%

    No Known Activations