© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 42718
    Prev
    Next
    INDEX
    Explanations

    sees a

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

    The neuron fires on the third‐person singular present‐tense verb “sees.”

    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
    i
    -2.77
    洐
    -2.69
    k
    -2.59
    0
    -2.44
    ”
    -2.36
     see
    -2.25
    e
    -2.23
     einige
    -2.13
     полиции
    -2.11
    ta
    -2.09
    POSITIVE LOGITS
    "
    2.55
     sees
    2.52
    ︓
    2.39
    无论
    2.28
    不论
    2.25
    '
    2.23
    是
    2.16
     It
    2.13
     crossorigin
    2.11
    独特
    2.09
    Activations Density 0.001%

    No Known Activations