© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41462
    Prev
    Next
    INDEX
    Explanations

    entities and names

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

    The neuron fires strongly on capitalized name fragments—i.e. tokens that are parts of proper nouns (people or place names).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     avec
    -3.00
     ("
    -2.81
     "
    -2.69
    勦
    -2.39
    ↵↵
    -2.28
    {
    -2.25
     "-
    -2.25
     "$
    -2.19
     в
    -2.17
     "#
    -2.17
    POSITIVE LOGITS
    and
    4.22
    ?”
    2.97
    。」
    2.92
    also
    2.77
    𓆏
    2.58
     inginkan
    2.48
    あた
    2.47
     navires
    2.44
    梣
    2.34
    including
    2.33
    Activations Density 0.012%

    No Known Activations