© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67203
    Prev
    Next
    INDEX
    Explanations

    until [time or state]

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

    This neuron strongly activates on numeric measurement tokens (e.g. quantities, times, temperatures, especially decimal or multi-digit values) in instructional text.

    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
     weathered
    -1.70
     irmão
    -1.68
    
    -1.62
     kapak
    -1.55
    恁
    -1.54
    枼
    -1.53
    ⑊
    -1.52
     sujeito
    -1.52
     畳
    -1.52
    卝
    -1.50
    POSITIVE LOGITS
     first
    2.03
     until
    1.99
     after
    1.91
     when
    1.88
     by
    1.63
     since
    1.56
     before
    1.56
     If
    1.56
    If
    1.55
    .
    1.54
    Activations Density 0.011%

    No Known Activations