© 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. 40410
    Prev
    Next
    INDEX
    Explanations

    Don prefixes

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

    The neuron fires on occurrences of the honorific title “Don” (as in “Don Bernardo,” “Don Miguel,” etc.) in front of personal 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
    )
    -1.88
     daihatsu
    -1.52
     doraemon
    -1.48
     والتي
    -1.47
    ie
    -1.41
     haup
    -1.41
     strix
    -1.38
     uwe
    -1.33
     ktm
    -1.32
     gsx
    -1.31
    POSITIVE LOGITS
    𖣔
    1.48
     as
    1.46
     ahora
    1.45
    пят
    1.34
     antichi
    1.34
     hanya
    1.31
    ökning
    1.29
    виа
    1.28
     lumière
    1.26
    金色
    1.26
    Activations Density 0.010%

    No Known Activations