© 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. 47754
    Prev
    Next
    INDEX
    Explanations

    people

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

    The neuron fires on occurrences of the word “people.”

    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
     sorprender
    -1.52
     sobrevivir
    -1.48
    adə
    -1.48
     soportar
    -1.48
     gutem
    -1.39
     gustar
    -1.39
     belki
    -1.38
    widetext
    -1.38
    }$
    -1.36
    ");//
    -1.36
    POSITIVE LOGITS
    .
    1.77
     ``
    1.48
    /
    1.41
     ‘‘
    1.30
    新た
    1.30
    他还
    1.27
    istocene
    1.27
    「
    1.27
    …？
    1.24
    <0xD4>
    1.23
    Activations Density 0.119%

    No Known Activations