© 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. 68943
    Prev
    Next
    INDEX
    Explanations

    starting phrases and code constructs

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

    This neuron detects LaTeX-style mathematical markup commands (e.g. “\stackrel,” “\underset,” arrow commands) embedded in text.

    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
    ﾚ
    -2.44
    身影
    -2.19
    ем
    -2.17
     pelaksanaan
    -2.13
    i
    -2.03
    я
    -2.03
     शुर
    -2.02
     setempat
    -2.00
     shows
    -1.97
     oversized
    -1.96
    POSITIVE LOGITS
    er
    2.69
    {
    2.45
    錞
    2.31
    俛
    2.22
    渐渐
    2.20
     Advantages
    2.19
     Helpful
    2.16
    “
    2.14
    紧接着
    2.09
     بالإضافة
    2.05
    Activations Density 0.000%

    No Known Activations