© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13832
    Prev
    Next
    INDEX
    Explanations

    latex math and code syntax

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

    The neuron activates on numeric literals (especially floating‐point values and dimension specifications) in code or markup.

    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
    ↵↵↵
    -1.63
     dando
    -1.51
    すごく
    -1.41
     fazendo
    -1.38
    olved
    -1.36
    铙
    -1.32
     شهاد
    -1.32
    niająca
    -1.31
    र्
    -1.30
    )
    -1.30
    POSITIVE LOGITS
     ONLY
    2.06
     only
    2.05
     this
    1.64
     what
    1.56
    Only
    1.55
    Despite
    1.54
     bzw
    1.53
     where
    1.50
     with
    1.48
     Despite
    1.48
    Activations Density 0.007%

    No Known Activations