© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 128040
    Prev
    Next
    INDEX
    Explanations

    mathematical properties and theorems

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

    The neuron fires on technical mathematical phrases stating problems or results—especially terms like “norm,” “bounds,” “sharp,” and related language introducing a theorem or estimate.

    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
    這些
    -1.37
    ícias
    -1.37
     vorhandenen
    -1.34
     immediately
    -1.34
    かは
    -1.33
     vegetación
    -1.28
    內的
    -1.27
     maceta
    -1.24
     incendios
    -1.21
     ventilación
    -1.20
    POSITIVE LOGITS
     of
    1.67
     also
    1.66
     and
    1.61
     in
    1.58
     for
    1.57
     even
    1.57
     sogar
    1.48
     одежда
    1.38
     Neither
    1.38
     privat
    1.36
    Activations Density 0.514%

    No Known Activations