© 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. 130577
    Prev
    Next
    INDEX
    Explanations

    This neuron flags domain-specific scientific terms and section headings (e.g. “Literature,” “activity,” “derivatives,” “expression,” “Induction”) typical of biomedical research text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    gene expression levels

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

    This neuron detects scientific text related to biological or medical research, particularly focusing on technical terminology in academic papers.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     luks
    -1.33
     Pilihan
    -1.33
     eksklu
    -1.28
     Sekarang
    -1.25
     Layanan
    -1.24
     Kebijakan
    -1.24
     หนัง
    -1.22
     menyen
    -1.22
     harap
    -1.20
     etui
    -1.20
    POSITIVE LOGITS
    (
    1.11
     (
    1.05
     duly
    1.05
     while
    1.03
     stipulated
    1.03
     taking
    1.00
    <<<<<<<
    0.97
     with
    0.96
     using
    0.95
     on
    0.95
    Activations Density 0.591%

    No Known Activations