© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20590
    Prev
    Next
    INDEX
    Explanations

    Sinatra, Heathrow, Sopranos, Skywalker, soprano

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

    The neuron activates on named entities—proper nouns like people’s names, place names, and titles.

    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
    〼
    -2.84
     enamorado
    -2.64
    卨
    -2.55
     Meksika
    -2.53
    ❢
    -2.42
     醬
    -2.36
    Specifik
    -2.28
     ansatte
    -2.27
    Antworten
    -2.25
     Если
    -2.22
    POSITIVE LOGITS
    ↵
    3.47
    .
    2.86
     we
    2.81
    葙
    2.70
     vorigen
    2.67
     to
    2.55
    i
    2.36
     einschließlich
    2.31
    from
    2.23
    as
    2.22
    Activations Density 0.003%

    No Known Activations