© 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. 13269
    Prev
    Next
    INDEX
    Explanations

    chemical substances and tumors

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

    The neuron detects chemical compounds and pharmaceutical terms like "chloroform," "calciferol," "aspirin," and other scientific terminology in technical documents.

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

    The neuron strongly activates on specialized technical or scientific terms (e.g. chemical names, medical/biological compounds, file‐header identifiers, etc.).

    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
    '
    -4.03
    o
    -4.00
    y
    -3.98
    2
    -3.91
    (
    -3.59
    <
    -3.55
    h
    -3.50
    id
    -3.45
            
    -3.36
    9
    -3.28
    POSITIVE LOGITS
     शुर
    3.20
    柃
    3.09
    罍
    3.09
    柺
    3.08
    璆
    3.08
    梣
    2.89
    ஂ
    2.86
    垻
    2.84
    ⮜
    2.83
    缦
    2.81
    Activations Density 0.016%

    No Known Activations