© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 40396
    Prev
    Next
    INDEX
    Explanations

    gynecology

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

    names of places, particularly cities and towns, especially those with distinctive or non-English names.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on proper nouns—especially named entities like place names and acronyms.

    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
    [
    -3.52
    _
    -3.38
    *
    -3.33
    '
    -2.95
    ).
    -2.89
    ?
    -2.70
    悄
    -2.64
    \
    -2.61
    <
    -2.61
            
    -2.59
    POSITIVE LOGITS
    梦见
    2.69
     These
    2.64
    ogues
    2.58
    我们的
    2.47
     排骨
    2.41
     сист
    2.38
    蜮
    2.38
    ּ
    2.34
    ꯸
    2.33
    кроссовки
    2.30
    Activations Density 0.034%

    No Known Activations