© 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. 10-GEMMASCOPE-RES-131K
    7. 119030
    Prev
    Next
    INDEX
    Explanations

    cholinergic and atropine

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

    pharmaceutical and chemical compounds related to neurotransmitters and receptor antagonists, especially cholinergic drugs.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     there
    -1.76
     '
    -1.71
     Who
    -1.55
    </u>
    -1.55
    </code>
    -1.45
    લ
    -1.36
     day
    -1.34
     gestalten
    -1.31
    了吗
    -1.31
    вому
    -1.30
    POSITIVE LOGITS
     MessageBoxIcon
    1.59
    ⢅
    1.59
    腘
    1.48
    záll
    1.41
    målet
    1.40
     manifestación
    1.36
    registrer
    1.32
    ıza
    1.30
    Ⲉ
    1.30
     Ancak
    1.28
    Activations Density 0.140%

    No Known Activations