© 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. 67675
    Prev
    Next
    INDEX
    Explanations

    mathematical and programming symbols

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

    Explanation of neuron 4 behavior: the main thing this neuron does is find instances of the square‐root operator (e.g. “sqrt”).

    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
     Anſ
    -1.77
    哧
    -1.67
     semelh
    -1.67
    probably
    -1.66
     decidedly
    -1.64
    aning
    -1.64
    EdgeInsets
    -1.63
     tumultuous
    -1.63
    ೢ
    -1.62
    桫
    -1.61
    POSITIVE LOGITS
     or
    2.86
     while
    1.78
     after
    1.72
    .”
    1.58
     despite
    1.57
     adds
    1.51
     before
    1.51
     could
    1.49
    </em>
    1.48
     increases
    1.46
    Activations Density 0.024%

    No Known Activations