© 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. 8753
    Prev
    Next
    INDEX
    Explanations

    surnames ending in erson

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

    This neuron detects tokens ending in the string “erson,” typically surnames or proper names ending with “-erson.”

    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
    >
    -3.13
    "
    -3.09
    u
    -2.81
    }$
    -2.55
     If
    -2.41
     otras
    -2.25
    RenderAtEndOf
    -2.25
     You
    -2.25
    лся
    -2.23
    i
    -2.20
    POSITIVE LOGITS
    ௅
    2.61
    趼
    2.59
    ⢓
    2.59
     valentín
    2.39
    グルト
    2.38
    这也
    2.38
    ୌ
    2.38
    割と
    2.34
     rekon
    2.31
    งิน
    2.30
    Activations Density 0.012%

    No Known Activations