© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 43863
    Prev
    Next
    INDEX
    Explanations

    latex math symbols and environments

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

    This neuron fires on occurrences of the “Bbb” token (i.e. LaTeX’s blackboard‐bold/mathbb notation).

    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
    *
    -1.95
     You
    -1.77
     &
    -1.69
     Of
    -1.60
     Your
    -1.55
    —
    -1.51
     A
    -1.49
    L
    -1.48
     The
    -1.46
     которую
    -1.46
    POSITIVE LOGITS
    CION
    1.53
    媖
    1.50
    inerario
    1.48
     mengakui
    1.46
     Atención
    1.46
    鶺
    1.42
    íše
    1.41
    釹
    1.41
    ƍ
    1.38
    "))
    
    1.37
    Activations Density 0.012%

    No Known Activations