© 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. 80974
    Prev
    Next
    INDEX
    Explanations

    scientific and medical concepts

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

    technical or scientific terms in academic papers, particularly related to devices, systems, and biological mechanisms.

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

    The neuron fires strongly on specialized, multi‐syllable scientific or technical terms (e.g. “resistance,” “rehabilitation,” “devices,” “particles”) characteristic of research‐paper language.

    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
     this
    -1.77
     actually
    -1.56
     perhaps
    -1.51
     really
    -1.47
     didn
    -1.45
     will
    -1.41
     doesn
    -1.39
     other
    -1.38
     just
    -1.38
     wouldn
    -1.38
    POSITIVE LOGITS
    often
    1.29
    有很多
    1.27
    Nowadays
    1.23
    越来越
    1.20
     has
    1.19
    maktadır
    1.18
     رغم
    1.16
     souvent
    1.13
    一直
    1.11
     spesso
    1.10
    Activations Density 3.290%

    No Known Activations