© 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. 22477
    Prev
    Next
    INDEX
    Explanations

    any followed by another word

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

    The neuron activates on the determiner “any.”

    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
     почина
    -1.52
     Koffer
    -1.44
     being
    -1.43
     користу
    -1.40
     використовувати
    -1.40
     soportar
    -1.35
     розта
    -1.35
     forefront
    -1.34
     Schreiben
    -1.33
     кілька
    -1.33
    POSITIVE LOGITS
     other
    2.89
     autre
    1.77
     weiteren
    1.66
     Autres
    1.61
     других
    1.59
    其他
    1.55
     annan
    1.52
    ным
    1.51
     innych
    1.50
    weetened
    1.49
    Activations Density 0.019%

    No Known Activations