© 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. 68067
    Prev
    Next
    INDEX
    Explanations

    describing how things are done

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

    This neuron specifically activates on occurrences of the word “ways.”

    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
     encontrado
    -2.78
    媵
    -2.55
    瑱
    -2.52
    仨
    -2.50
     localizado
    -2.50
     controlada
    -2.48
    祆
    -2.45
     aldus
    -2.44
     ſie
    -2.44
    iſter
    -2.42
    POSITIVE LOGITS
    s
    3.77
    It
    3.38
     ways
    2.91
    We
    2.80
    In
    2.73
    你
    2.72
    我
    2.56
    my
    2.53
    name
    2.52
    At
    2.45
    Activations Density 0.010%

    No Known Activations