© 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. 10-GEMMASCOPE-RES-131K
    7. 3742
    Prev
    Next
    INDEX
    Explanations

    Telerik, eBook, IPCC, nanomaterials

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

    proper nouns and technical terminology in various domains like technology, materials science, and product names.

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

    The neuron activates on capitalized proper nouns and technical names (e.g. product names, acronyms, institutions).

    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
     начали
    -2.97
    》、《
    -2.55
     That
    -2.48
    }{
    -2.39
    ziná
    -2.38
    )$
    -2.38
    ')
    -2.36
    felpa
    -2.36
     трудно
    -2.33
    </h5>
    -2.31
    POSITIVE LOGITS
    ’
    4.09
    菒
    2.86
    We
    2.52
    ’;
    2.27
     was
    2.27
    ’，
    2.25
     didnt
    2.22
    蟊
    2.20
    廛
    2.17
     colgantes
    2.14
    Activations Density 0.023%

    No Known Activations