© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107254
    Prev
    Next
    INDEX
    Explanations

    Simultaneously, acute, sequences

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

    This neuron detects LaTeX math‐mode structural tokens (such as braces, underscores, backslashes, and related 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_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
    逃跑
    -0.80
     held
    -0.77
     elett
    -0.77
     beiden
    -0.75
    beim
    -0.74
     Held
    -0.74
     categoryId
    -0.74
    طان
    -0.73
    empêcher
    -0.73
    少しでも
    -0.73
    POSITIVE LOGITS
    \}_{
    0.94
    })_{
    0.83
    )_{
    0.82
     assemb
    0.79
    tacles
    0.79
     larg
    0.78
    kách
    0.77
     Händen
    0.75
    збе
    0.75
    amura
    0.74
    Activations Density 0.013%

    No Known Activations