© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 128463
    Prev
    Next
    INDEX
    Explanations

    administrative divisions and centers

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

    This neuron detects mentions of administrative territorial units (e.g. “administrative division,” “district,” “center,” etc.).

    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
     when
    -1.69
    yship
    -1.47
    styleable
    -1.42
    queryInterface
    -1.39
     año
    -1.39
    ruptedException
    -1.34
    titial
    -1.31
     cuando
    -1.29
    blurRadius
    -1.27
     comum
    -1.27
    POSITIVE LOGITS
     there
    1.36
     zobac
    1.24
     pantalón
    1.20
    おもちゃ
    1.18
    それにしても
    1.15
     szybko
    1.13
    還沒
    1.12
     of
    1.10
    pantalon
    1.09
    さっき
    1.09
    Activations Density 0.069%

    No Known Activations