© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40032
    Prev
    Next
    INDEX
    Explanations

    locale

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

    The neuron specifically detects occurrences of the word “locale.”

    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
    ’,
    -3.55
    玙
    -2.91
    饪
    -2.77
    蟜
    -2.75
    賒
    -2.72
     GOtt
    -2.59
    \">
    -2.55
    ,’
    -2.50
    ﹑
    -2.50
    ],
    -2.45
    POSITIVE LOGITS
    逦
    2.70
     recepción
    2.42
     '
    2.42
    涙
    2.38
    ſelves
    2.30
    S
    2.28
     土産
    2.22
    ⸩
    2.19
     ежедневно
    2.16
    ăzi
    2.09
    Activations Density 0.003%

    No Known Activations