© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 104156
    Prev
    Next
    INDEX
    Explanations

    Sichuan province or Japanese place names

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

    The neuron strongly activates on each occurrence of the place name “Sichuan” (notably when it’s tagged with a following reference or footnote number).

    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
    0
    -3.64
    
    -2.77
    𖣘
    -2.48
    ”
    -2.42
    峮
    -2.38
    大多
    -2.22
    歘
    -2.22
    </strong>
    -2.19
    And
    -2.17
    艄
    -2.14
    POSITIVE LOGITS
     zove
    2.52
     opro
    2.48
     nadru
    2.44
     unwelcome
    2.39
    ről
    2.38
     meest
    2.34
     dwindling
    2.33
    芎
    2.31
    ETTI
    2.28
     ktorí
    2.27
    Activations Density 0.003%

    No Known Activations