© 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. 7174
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notation

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

    The neuron activates on LaTeX/math markup tokens (e.g. \mathrm, \mathbb, mathematical symbols and commands).

    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
               
    -1.90
    |$.
    -1.80
    }}.
    -1.73
                 
    -1.67
    ८
    -1.66
    ︲
    -1.66
     específica
    -1.66
    ְּ
    -1.63
             
    -1.63
     использования
    -1.63
    POSITIVE LOGITS
     with
    2.06
    Esperamos
    1.88
     Cualquier
    1.84
    饷
    1.80
    från
    1.73
    ὴν
    1.73
    暧
    1.73
     Aseg
    1.73
    亟
    1.72
    𝖌
    1.70
    Activations Density 0.025%

    No Known Activations