© 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. 41519
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units

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

    The neuron specifically fires on the hyphen token when it appears linking numbers (e.g. in numeric ranges).

    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
    </strong>
    -2.77
    0
    -2.52
    {
    -2.52
    1
    -2.45
    —
    -2.22
    …
    -2.19
    )
    -2.17
     During
    -2.16
    ’
    -2.08
    ↵
    -2.02
    POSITIVE LOGITS
    嗵
    2.08
     certains
    2.06
     rám
    2.03
    部分は
    1.99
    愎
    1.95
     essentiel
    1.91
    镚
    1.89
     multitud
    1.85
    咘
    1.85
    ICIOS
    1.84
    Activations Density 0.052%

    No Known Activations