© 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. 22-GEMMASCOPE-RES-131K
    7. 14500
    Prev
    Next
    INDEX
    Explanations

    locale settings

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

    The neuron specifically activates on occurrences of the term “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_22/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
    ro
    -2.84
    ’,
    -2.64
    s
    -2.61
    ],
    -2.56
    嫱
    -2.50
     Incidentally
    -2.48
     However
    -2.33
    ).
    -2.31
    \">
    -2.30
    new
    -2.28
    POSITIVE LOGITS
    ſu
    2.97
    逦
    2.70
     pourront
    2.33
     pièces
    2.11
    鶿
    2.09
     土産
    2.08
    ￬
    2.06
    涙
    2.03
    гули
    2.03
     interessante
    2.03
    Activations Density 0.008%

    No Known Activations