© 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. 102863
    Prev
    Next
    INDEX
    Explanations

    code footnotes bibliography markers

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

    This neuron detects backslash characters, i.e. LaTeX or markup command prefixes.

    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
     cudd
    -2.25
    </em>
    -2.05
    ↵↵
    -2.03
    '
    -1.90
    ;
    -1.90
    $
    -1.89
    .
    -1.88
     Each
    -1.80
     następnie
    -1.77
    R
    -1.76
    POSITIVE LOGITS
    𖣘
    2.39
    蹓
    2.34
    賔
    2.30
    ⡪
    2.22
     preventivo
    2.09
    寕
    2.09
     quotidi
    2.02
     手绘
    2.02
    躂
    1.96
     admon
    1.95
    Activations Density 0.010%

    No Known Activations