© 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. 60321
    Prev
    Next
    INDEX
    Explanations

    fatal myocardial infarction

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

    programming and code-related content, particularly focusing on syntax like quotes, function names, and file paths.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on code‐tokens—e.g. programming identifiers, language names, and object/property names in code or markup.

    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
     while
    -0.76
    ავ
    -0.75
    TMS
    -0.75
     hålla
    -0.73
    inė
    -0.73
    قامت
    -0.73
    ötzlich
    -0.73
     budgeting
    -0.72
    صاب
    -0.71
     Fuels
    -0.71
    POSITIVE LOGITS
     Missouri
    0.91
    ᄆ
    0.86
    Ể
    0.81
    章节
    0.78
    igers
    0.77
     Banglades
    0.77
    Missouri
    0.76
     EU
    0.76
     JU
    0.75
    pojo
    0.75
    Activations Density 0.000%

    No Known Activations