© 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. 22-GEMMASCOPE-RES-131K
    7. 73914
    Prev
    Next
    INDEX
    Explanations

    LaTeX article preamble

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

    The neuron flags numeric quantities (including measurement units like “mm”) in technical/LaTeX documents.

    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
    OOO
    -1.02
    vaila
    -1.00
     höl
    -0.98
     květ
    -0.97
     Jahrhunderts
    -0.95
     darbu
    -0.94
    hills
    -0.93
    jfree
    -0.93
    ものの
    -0.92
     "";
    -0.92
    POSITIVE LOGITS
     dessutom
    1.04
     Україні
    0.95
    uyor
    0.95
     manifestly
    0.94
    kwds
    0.93
    quilo
    0.90
    TAINS
    0.90
    lanmış
    0.90
     enunci
    0.89
     zeigen
    0.88
    Activations Density 0.005%

    No Known Activations