© 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. 40476
    Prev
    Next
    INDEX
    Explanations

    colon and semicolon punctuation

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

    The neuron fires on specialized mathematical notation tokens—e.g. colons in function definitions, “dots” (ellipsis) markers, and Dirac‐ket symbols (“|…〉”)—in LaTeX/math contexts.

    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
    '
    -2.73
    In
    -2.36
     hoher
    -2.34
     jedem
    -2.25
    很容易
    -2.20
     own
    -2.13
    部分
    -2.11
    3
    -2.11
    更多的
    -2.03
     demselben
    -2.02
    POSITIVE LOGITS
    紆
    2.47
     vermel
    2.38
    zation
    2.28
    猡
    2.27
    takt
    2.25
    쑹
    2.25
     队
    2.20
     Feinde
    2.20
     Bereichen
    2.17
    枼
    2.14
    Activations Density 0.002%

    No Known Activations