© 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. 61242
    Prev
    Next
    INDEX
    Explanations

    pretreatment and angiograms

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

    medical imaging and treatment preparation terminology, particularly "pretreatment" and "angiogram" words.

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

    The neuron primarily detects occurrences of the word “pretreatment.”

    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
    a
    -3.61
    н
    -3.19
    an
    -2.88
    ৢ
    -2.73
     {
    -2.56
    から
    -2.52
    を
    -2.50
    one
    -2.50
    ↵↵
    -2.45
     avec
    -2.41
    POSITIVE LOGITS
    
    2.55
    </h3>
    2.52
     土産
    2.48
     Gegensatz
    2.31
     According
    2.31
    selben
    2.23
     lavabo
    2.23
     tabac
    2.22
    鲥
    2.20
    区别
    2.19
    Activations Density 0.020%

    No Known Activations