© 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. 73124
    Prev
    Next
    INDEX
    Explanations

    field followed by prepositions

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

    The neuron activates on occurrences of the words “field” or “fields.”

    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
    ,
    -2.22
    .
    -2.13
     approche
    -1.91
     autorisation
    -1.80
     idée
    -1.78
    ✽
    -1.74
    絰
    -1.65
    Ꮟ
    -1.64
     止
    -1.63
    Proceedings
    -1.61
    POSITIVE LOGITS
     kemudian
    2.09
    のみ
    1.93
     può
    1.90
     algumas
    1.89
    了很多
    1.79
     possu
    1.79
     terkait
    1.78
     encontram
    1.78
     possuem
    1.78
     to
    1.77
    Activations Density 0.069%

    No Known Activations