© 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. 34-GEMMASCOPE-RES-131K
    7. 31719
    Prev
    Next
    INDEX
    Explanations

    mathematical implications using symbols

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

    This neuron detects LaTeX‐style math notation—especially backslash commands, math‐mode operators, and variable names within math formulas.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ){}
    -0.98
    depends
    -0.94
    depending
    -0.91
     restant
    -0.89
    scheduler
    -0.88
     incluem
    -0.87
    either
    -0.86
    blau
    -0.86
     Tweede
    -0.85
     agir
    -0.84
    POSITIVE LOGITS
    Rightarrow
    2.66
     implies
    2.58
     =>
    2.33
     implication
    1.99
     ⇒
    1.96
    implies
    1.95
     implications
    1.94
     so
    1.91
    Longrightarrow
    1.87
    ⇒
    1.81
    Activations Density 0.029%

    No Known Activations