© 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. 22-GEMMASCOPE-RES-131K
    7. 13518
    Prev
    Next
    INDEX
    Explanations

    code and biology

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

    closing curly braces and endif statements in programming code.

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

    The neuron is keyed to assignment operators (the “=” token) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     especially
    -0.91
    especially
    -0.91
     especialmente
    -0.88
     zwłaszcza
    -0.84
     particularly
    -0.83
    /*++
    -0.81
    苛
    -0.81
     مردانه
    -0.81
     Houses
    -0.80
    particularly
    -0.80
    POSITIVE LOGITS
    .*;
    1.07
     모두
    1.00
    いずれ
    1.00
    คือ
    0.92
    说到
    0.89
    alike
    0.87
     đều
    0.87
    女性
    0.85
    الیا
    0.85
    /**
    0.84
    Activations Density 0.008%

    No Known Activations