© 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. 10971
    Prev
    Next
    INDEX
    Explanations

    political science and tamoxifen

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

    academic disciplines, particularly "political science" and scientific terms like "tamoxifen" and "Corynebacterium".

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

    The neuron activates on multiword technical or scientific terms (e.g., drug names like “tamoxifen,” field names like “Political Science,” or species names such as “Corynebacterium glutamicum”).

    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
    ᯅ
    -2.17
     dichas
    -2.11
    Ꮒ
    -2.00
     Sortiment
    -1.97
    e
    -1.96
    ﺅ
    -1.95
    èvement
    -1.91
    ...?
    -1.88
    '?
    -1.88
     frecuentemente
    -1.88
    POSITIVE LOGITS
    \
    2.16
     anderen
    1.96
    犼
    1.90
    </b>
    1.90
    _
    1.90
    
    1.82
    袛
    1.81
    笵
    1.77
    ೣ
    1.77
    鹋
    1.77
    Activations Density 0.057%

    No Known Activations