© 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. 69313
    Prev
    Next
    INDEX
    Explanations

    volunteers help and participate

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

    The neuron detects mentions of the word “volunteer” (in its singular or plural forms).

    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
    翃
    -2.58
    錼
    -2.53
     we
    -2.47
    '
    -2.47
    要求
    -2.47
    }$
    -2.41
     当
    -2.30
     在
    -2.30
     unglaub
    -2.30
     consider
    -2.28
    POSITIVE LOGITS
    ⢓
    2.84
    酲
    2.70
    淠
    2.61
    酝
    2.59
     スープ
    2.58
    灕
    2.56
    --"
    2.52
     火鍋
    2.48
    <i>
    2.45
    芣
    2.42
    Activations Density 0.005%

    No Known Activations