© 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. 75510
    Prev
    Next
    INDEX
    Explanations

    made up of

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

    This neuron detects phrases that specify composition by number—especially “made up of” followed by a numeric quantity.

    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
    .
    -2.36
    ,”
    -2.31
    So
    -2.09
    This
    -2.03
     of
    -1.97
    🤪
    -1.95
    There
    -1.95
    ↵↵
    -1.88
    In
    -1.84
     Jenderal
    -1.82
    POSITIVE LOGITS
    </strong>
    2.55
    翆
    2.38
    を使用した
    2.20
     WOULD
    2.19
    跸
    2.17
    蹀
    2.08
     naciones
    2.03
    趼
    2.03
    卺
    2.03
     แต่
    1.98
    Activations Density 0.016%

    No Known Activations