© 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. 100906
    Prev
    Next
    INDEX
    Explanations

    partner followed by certain words

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

    This neuron selectively fires on occurrences of the substring “partner” (e.g. “Partner,” “partners,” “partnerNumber,” etc.) in various contexts.

    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
    .
    -2.25
     in
    -2.06
     cuidadosamente
    -1.99
     necesariamente
    -1.98
     большая
    -1.97
     wohin
    -1.94
    беріга
    -1.94
     apparent
    -1.88
     now
    -1.88
     muchísimo
    -1.85
    POSITIVE LOGITS
     valentín
    2.55
    from
    2.16
    quelize
    2.06
    up
    2.05
    partner
    2.00
    也将
    1.94
    medriver
    1.93
     мог
    1.91
    ではでは
    1.90
    na
    1.88
    Activations Density 0.028%

    No Known Activations