© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70223
    Prev
    Next
    INDEX
    Explanations

    biomedical fields and topics

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

    The neuron detects references to biomedical research, engineering, or science in academic contexts.

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

    The neuron selectively activates on the term “biomedical” (e.g. in compounds like “biomedical research,” “biomedical engineering,” etc.).

    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
    "
    -2.97
     are
    -2.44
    
    -2.34
     et
    -2.31
     ſaid
    -2.28
    ).
    -2.19
     ziemlich
    -2.14
    
    -2.09
     "
    -2.06
    ")
    -2.02
    POSITIVE LOGITS
    逦
    2.56
    镡
    2.34
     mereka
    2.30
    AÇÃO
    2.23
    焿
    2.19
     camiset
    2.08
    ୃ
    2.06
     and
    2.02
    却又
    2.02
    etts
    1.98
    Activations Density 0.008%

    No Known Activations