© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101422
    Prev
    Next
    INDEX
    Explanations

    hetero + dimer or zygous

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

    The neuron detects scientific terms referring to heterodimeric molecular structures (like heterodimer, heterozygous) in academic biology text.

    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
    \
    -3.02
     If
    -2.58
    (
    -2.52
    "
    -2.47
      
    -2.33
    ↵↵
    -2.25
    ghalaya
    -2.23
    en
    -2.23
     AND
    -2.22
     kteří
    -2.19
    POSITIVE LOGITS
    久し
    2.73
     colgantes
    2.56
    和她
    2.53
     silencioso
    2.52
    屢
    2.48
     multiuso
    2.42
     レスト
    2.42
     luminoso
    2.39
     modellen
    2.39
    想了想
    2.34
    Activations Density 0.003%

    No Known Activations