© 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. 10-GEMMASCOPE-RES-131K
    7. 130880
    Prev
    Next
    INDEX
    Explanations

    mathematical equations alignment

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

    This neuron fires on tokens that are part of code or LaTeX‐style mathematical markup (e.g. “eq”, “align”, “ɛ”, “esac”).

    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
    </td>
    -2.38
    ⚣
    -2.22
    และ
    -2.14
    玗
    -2.08
    朏
    -2.03
     și
    -2.00
    诡
    -1.97
    昞
    -1.97
     ſte
    -1.95
    ญี่ป
    -1.95
    POSITIVE LOGITS
    2
    2.25
    的
    2.09
    F
    1.95
    3
    1.91
    y
    1.87
    D
    1.83
     critically
    1.82
    そのため
    1.82
    1
    1.81
     are
    1.80
    Activations Density 0.001%

    No Known Activations