© 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. 65690
    Prev
    Next
    INDEX
    Explanations

    medical and genetic conditions

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

    medical and scientific terminology related to body systems, drugs, and biological processes.

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

    The neuron is strongly activated by specialized scientific jargon—especially technical biomedical and research-oriented nouns.

    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
     potentiel
    -1.41
     originalen
    -1.20
     chêne
    -1.20
     vorigen
    -1.20
     bambou
    -1.18
     dét
    -1.16
    螄
    -1.13
     emballage
    -1.09
     marbre
    -1.09
     arbre
    -1.09
    POSITIVE LOGITS
     and
    1.47
     επίσης
    1.29
    Why
    1.23
    ៍
    1.20
    When
    1.20
     그것
    1.19
     Gestaltung
    1.18
     также
    1.18
    This
    1.17
    With
    1.15
    Activations Density 0.282%

    No Known Activations