© 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. 61342
    Prev
    Next
    INDEX
    Explanations

    proverbs and sayings

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

    The neuron fires when encountering references to traditional sayings, proverbs, or adages.

    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
     évidence
    -1.88
    🦣
    -1.82
    柺
    -1.77
    faßt
    -1.77
    ﮯ
    -1.74
    ்கு
    -1.72
    笮
    -1.72
    ꦢ
    -1.72
    镠
    -1.70
    廼
    -1.69
    POSITIVE LOGITS
    It
    2.58
    .
    2.34
    <i>
    2.25
     Consejos
    1.94
    If
    1.89
    ￪
    1.81
     estadounidenses
    1.81
    3
    1.80
    5
    1.78
    2
    1.77
    Activations Density 0.003%

    No Known Activations