© 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. 59667
    Prev
    Next
    INDEX
    Explanations

    Carl Riskin, Luis Mariano, Bitchard Pryor

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

    The neuron detects numeric tokens—quantities, statistics, scores, years, percentages, etc.

    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
     our
    -1.66
     또
    -1.48
    rası
    -1.46
    Več
    -1.44
    Réponse
    -1.41
    uniqlo
    -1.41
     another
    -1.41
     மற்ற
    -1.39
     obé
    -1.38
    ⋙
    -1.38
    POSITIVE LOGITS
     –
    2.22
    mathrm
    1.60
     â
    1.46
     —
    1.40
     -
    1.39
     •
    1.38
      
    1.37
    ।
    1.36
     to
    1.35
    ==""){
    1.34
    Activations Density 0.073%

    No Known Activations