© 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. 69393
    Prev
    Next
    INDEX
    Explanations

    volunteer activity

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

    The neuron detects mentions of volunteering (e.g. “volunteer,” “volunteers,” “volunteering”) and related contexts.

    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
    '
    -2.02
     some
    -1.59
     two
    -1.58
     major
    -1.58
     asegu
    -1.57
     When
    -1.55
     their
    -1.53
     einzigartige
    -1.47
     about
    -1.46
     several
    -1.41
    POSITIVE LOGITS
    --"
    2.25
    ᆞ
    1.95
    <i>
    1.82
    </sub>
    1.75
    鹩
    1.72
    媜
    1.67
    ";
    1.65
    鶿
    1.65
    »;
    1.62
    動か
    1.62
    Activations Density 0.008%

    No Known Activations