© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 69003
    Prev
    Next
    INDEX
    Explanations

    oncogenes and oncoproteins

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

    words beginning with 'onco' related to cancer (like 'oncogenes', 'oncoprotein', 'oncofetal').

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

    The neuron consistently activates on the “onco” substring (the oncology-related prefix in words like oncogenes, oncolytic, oncoprotein, 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
    覿
    -2.52
    
    -2.34
    																								
    -2.28
    龶
    -2.25
    																										
    -2.22
     Including
    -2.20
    ИН
    -2.17
    】:
    -2.17
    ا
    -2.16
    輊
    -2.14
    POSITIVE LOGITS
    1
    2.64
     sabid
    2.59
    ዬ
    2.50
     –
    2.28
    懨
    2.19
     publicados
    2.17
    ’
    2.13
    而非
    2.13
     laajenta
    2.11
     使っ
    2.09
    Activations Density 0.041%

    No Known Activations