© 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. 34-GEMMASCOPE-RES-131K
    7. 106381
    Prev
    Next
    INDEX
    Explanations

    immune system / immune response

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

    citations in academic papers, particularly references to studies and authors.

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     inactivation
    -0.85
     triglycerides
    -0.82
     ritrov
    -0.81
     ballroom
    -0.79
     triglycer
    -0.79
     Greedy
    -0.77
    Eddy
    -0.77
     touchscreen
    -0.76
     capelli
    -0.76
     Desain
    -0.75
    POSITIVE LOGITS
     Immunol
    1.84
     Immunology
    1.51
     immun
    1.48
    immun
    1.23
     immune
    1.16
    Immun
    1.16
     Immun
    1.14
     immunos
    1.09
     IMM
    1.05
    Immune
    1.04
    Activations Density 0.083%

    No Known Activations