© 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. 22-GEMMASCOPE-RES-131K
    7. 67339
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and expressions

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

    This neuron fires on the custom infix “⊙” operation and its surrounding operand symbols (e.g. “a ⊙ b,” “0 ⊙ a”) in a formal algebraic definition.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ните
    -0.94
     abitanti
    -0.94
     this
    -0.94
     nzuri
    -0.91
     City
    -0.90
     این
    -0.90
     ",";
    -0.90
     if
    -0.90
     muhimu
    -0.89
    战队
    -0.88
    POSITIVE LOGITS
    álise
    1.09
    advised
    1.04
     is
    1.03
     inexist
    0.99
     communauté
    0.98
    asă
    0.97
    始めて
    0.96
     partie
    0.95
     aceptas
    0.95
    función
    0.94
    Activations Density 0.032%

    No Known Activations