© 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. 105404
    Prev
    Next
    INDEX
    Explanations

    colorectal cancer or polyps

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

    The neuron activates for the term "colorectal" when discussing cancer and medical research.

    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
     of
    -2.33
    {
    -2.25
        
    -2.23
    と
    -2.20
    \
    -2.08
    Sixty
    -1.99
     exodus
    -1.99
    ΠΑ
    -1.93
     avoids
    -1.89
                    
    -1.88
    POSITIVE LOGITS
     Then
    3.41
    眎
    3.09
    舠
    2.64
    ſelf
    2.47
     treu
    2.42
    ?"
    2.39
    ومت
    2.39
    嬷
    2.36
     juga
    2.34
    鼉
    2.34
    Activations Density 0.004%

    No Known Activations