© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65990
    Prev
    Next
    INDEX
    Explanations

    diseases and biological mechanisms

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

    scientific/medical article titles and their opening paragraphs about biological or genetic research.

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

    This neuron fires on the initial, capitalized term of a scientific paper or section title (i.e. the first big biomedical word in a title).

    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
     laine
    -1.33
    jshint
    -1.30
     oeil
    -1.26
     EYE
    -1.23
     yaka
    -1.19
     TEACHER
    -1.17
    Lain
    -1.16
     illustre
    -1.15
     fonde
    -1.15
     klinik
    -1.15
    POSITIVE LOGITS
    ”
    1.28
    ”,
    1.16
    E
    1.13
    Z
    1.13
    R
    1.13
    L
    1.11
    S
    1.10
    A
    1.09
    V
    1.09
    un
    1.08
    Activations Density 0.013%

    No Known Activations