© 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. 34-GEMMASCOPE-RES-131K
    4. 682
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and variables

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

    This neuron activates on LaTeX math‐mode formatting commands (e.g. backslash‐macros like \mathrm, \textrm and the following brace) used in mathematical expressions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     as
    -1.23
     which
    -1.11
     a
    -1.11
     to
    -1.08
     and
    -1.01
     an
    -0.97
     možnost
    -0.96
     ostensibly
    -0.95
     what
    -0.93
    旋律
    -0.90
    POSITIVE LOGITS
    וף
    1.03
    鳅
    1.01
    回来了
    0.95
     رجال
    0.95
    ㅛ
    0.94
    Blo
    0.94
    开了
    0.94
     pines
    0.93
    vanja
    0.93
     추가
    0.93
    Activations Density 0.005%

    No Known Activations