© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58048
    Prev
    Next
    INDEX
    Explanations

    hemopoietic cells, viral infection, vectors

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

    This neuron detects medical and biological terms related to blood cells and tissues, particularly "poietic" as in "hematopoietic" and "viral" terms.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered 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
    Negative Logits
    )++;
    -2.33
    犼
    -2.28
    ⚣
    -2.25
    zepine
    -2.05
    聼
    -2.02
    )",
    -2.00
    乄
    -1.96
    ፳
    -1.94
    泚
    -1.93
    >|</
    -1.89
    POSITIVE LOGITS
    .”
    2.61
    也
    2.30
    0
    2.08
    
    1.84
     補
    1.83
    要
    1.70
    形态
    1.70
     considerare
    1.70
    وضح
    1.70
    )
    1.68
    Activations Density 0.031%

    No Known Activations