© 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. 47936
    Prev
    Next
    INDEX
    Explanations

    definition of

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

    The neuron strongly activates on occurrences of the word “definition.”

    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
    )
    -2.55
    Sudah
    -2.48
     votre
    -2.44
     first
    -2.42
    CodeDom
    -2.41
     chaleur
    -2.39
    鬭
    -2.33
    |()
    -2.30
     pastikan
    -2.28
     cuisson
    -2.27
    POSITIVE LOGITS
    ”،
    3.36
    .
    3.30
    姈
    3.09
    ”?
    2.92
    )”
    2.80
     (“
    2.73
    ”)
    2.70
    酲
    2.69
    ”),
    2.69
     “
    2.69
    Activations Density 0.007%

    No Known Activations