© 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. 12372
    Prev
    Next
    INDEX
    Explanations

    factor and suppressor proteins

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

    This neuron activates for cancer biology terms, particularly oncogenes, tumor suppressors, and growth factors.

    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
     inz
    -1.57
     steen
    -1.55
    bedded
    -1.53
    ulence
    -1.48
     alho
    -1.47
     astonishing
    -1.45
     én
    -1.44
    alogical
    -1.42
     llo
    -1.42
     fers
    -1.41
    POSITIVE LOGITS
     their
    1.96
     while
    1.80
     While
    1.77
     these
    1.74
     Several
    1.70
    While
    1.64
     Numerous
    1.62
    Several
    1.62
     from
    1.60
     several
    1.60
    Activations Density 0.271%

    No Known Activations