© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 93020
    Prev
    Next
    INDEX
    Explanations

    HTML and LaTeX formatting characters

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

    The neuron is triggered by formatting or markup commands, especially backslash characters (e.g. LaTeX or HTML escapes).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     by
    -1.48
     was
    -1.23
     to
    -1.17
     его
    -1.15
     on
    -1.09
     campo
    -1.06
     its
    -1.04
    蛾
    -1.02
     suoi
    -1.01
    Koordinaten
    -1.01
    POSITIVE LOGITS
     sujeito
    1.16
     Gehalt
    1.04
    麻煩
    1.04
     véritables
    1.02
    columna
    1.02
     TResult
    1.01
    现在
    1.01
    先週
    1.00
     lót
    0.98
    </em>
    0.97
    Activations Density 0.001%

    No Known Activations