© 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. 104450
    Prev
    Next
    INDEX
    Explanations

    Som + names and medical terms

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

    The neuron detects names starting with "Som" like Somali, Somnath, Somdev, Somatosensory, or Somian.

    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
    ſſel
    -2.94
    也
    -2.80
    乆
    -2.58
    i
    -2.48
     vorigen
    -2.44
     professionelle
    -2.36
    ientras
    -2.30
    atnya
    -2.30
     sorprender
    -2.27
     invitar
    -2.23
    POSITIVE LOGITS
    </h2>
    2.67
     proactively
    2.58
     relentlessly
    2.45
     staunch
    2.42
    焢
    2.41
    ’
    2.38
    ăzi
    2.33
    \
    2.33
     comprehensively
    2.30
     unearth
    2.27
    Activations Density 0.013%

    No Known Activations