© 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. 85114
    Prev
    Next
    INDEX
    Explanations

    mathematical operator definitions

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

    The neuron fires on LaTeX command definitions and declarations (e.g. “\def”, “\DeclareMathOperator”, etc.).

    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
    告訴
    -1.36
    ING
    -1.35
     you
    -1.35
     ʻ
    -1.30
     одним
    -1.26
    \
    -1.21
    手伝
    -1.20
     He
    -1.20
    }(\
    -1.19
    われ
    -1.18
    POSITIVE LOGITS
    樘
    1.53
    Avoid
    1.46
    Примі
    1.45
     ſmall
    1.42
    隹
    1.39
    wouldn
    1.37
    iteit
    1.36
     appréci
    1.36
    曩
    1.35
     &___
    1.34
    Activations Density 0.012%

    No Known Activations