© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 57442
    Prev
    Next
    INDEX
    Explanations

    dozen items or quantities

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

    The neuron is triggered by explicit mentions of “dozen” (often with numerical modifiers) indicating counts of twelve or multiples thereof.

    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
     更
    -2.45
    廰
    -2.38
    釤
    -2.31
    ౮
    -2.25
    岨
    -2.25
    .
    -2.22
    豨
    -2.20
     finally
    -2.17
    雠
    -2.17
     sicura
    -2.14
    POSITIVE LOGITS
    ’
    2.27
    l
    2.17
     sehingga
    2.05
     of
    2.05
     potret
    2.02
    Pgina
    1.98
     (>
    1.94
     parezca
    1.93
    bilidad
    1.91
     dozen
    1.90
    Activations Density 0.004%

    No Known Activations