© 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. 10-GEMMASCOPE-RES-131K
    4. 110987
    Prev
    Next
    INDEX
    Explanations

    math and code structures

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

    the word "matrix" in mathematical or technical contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron activates on occurrences of the term “matrix.”

    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
    嫘
    -1.85
    мия
    -1.55
     eight
    -1.55
    隧道
    -1.53
     substantial
    -1.47
    ч
    -1.46
    ↵↵
    -1.41
    ikbaar
    -1.41
     regarding
    -1.38
     животные
    -1.38
    POSITIVE LOGITS
    驁
    1.99
     imposible
    1.66
    these
    1.62
    喈
    1.59
     intuiti
    1.57
     kein
    1.51
     demor
    1.51
     calcu
    1.49
     Milán
    1.45
    ῖ
    1.45
    Activations Density 0.000%

    No Known Activations