© 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. 22-GEMMASCOPE-RES-131K
    7. 73716
    Prev
    Next
    INDEX
    Explanations

    medical/technical terms and states

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

    medical and technical terminology related to bodily processes, mechanisms, and conditions.

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

    The neuron strongly activates on content‐rich, typically multi‐syllabic terms (especially technical or domain-specific nouns and keywords) rather than on short function words.

    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
     />,
    -1.09
     после
    -1.05
    clerosis
    -1.02
     it
    -1.02
    idenz
    -0.95
     подой
    -0.94
    schild
    -0.94
     cach
    -0.94
    bersicht
    -0.93
     its
    -0.92
    POSITIVE LOGITS
    OOTDTY
    1.19
    listes
    1.02
     pamamagitan
    1.02
     wartawan
    1.01
     consumidor
    1.00
     felb
    1.00
    bezpe
    0.99
     Belgische
    0.99
     juſt
    0.98
    liun
    0.98
    Activations Density 0.112%

    No Known Activations