© 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. 8325
    Prev
    Next
    INDEX
    Explanations

    puts Spanish sizes

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

    This neuron activates on the third‐person singular present tense verb “puts.”

    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
     to
    -1.86
     without
    -1.59
     the
    -1.51
     what
    -1.48
     after
    -1.45
     teck
    -1.43
     derzeit
    -1.43
     through
    -1.42
    教材
    -1.42
     but
    -1.40
    POSITIVE LOGITS
    ↵↵
    2.14
     you
    1.93
    enced
    1.80
     leyendas
    1.80
     tallas
    1.78
     definitiv
    1.70
     generaciones
    1.68
     antiguas
    1.66
     niñas
    1.63
     prendas
    1.61
    Activations Density 0.017%

    No Known Activations