© 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. 22-GEMMASCOPE-RES-131K
    4. 84016
    Prev
    Next
    INDEX
    Explanations

    regulatory strategies

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

    technical or specialized terms across different domains including computing, chemistry, physics, and materials science.

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

    The neuron strongly activates on isolated domain-specific or technical nouns (e.g. “switch,” “hydraulic,” “sulfite,” “cooling,” “regulatory,” “mohair,” “Burundi,” “gender”).

    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
    つづく
    -1.27
     folhas
    -1.09
    トヨタ
    -1.04
    にほんブログ村
    -0.99
     like
    -0.94
    hipster
    -0.94
    ürü
    -0.92
    購入した
    -0.91
     bancaria
    -0.91
     ótimo
    -0.90
    POSITIVE LOGITS
     그리고
    1.00
    ificantly
    0.93
    qa
    0.93
     all
    0.92
     العلاقات
    0.91
    ior
    0.91
    2
    0.89
     جميع
    0.88
    icons
    0.87
     Januari
    0.87
    Activations Density 0.074%

    No Known Activations