© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92777
    Prev
    Next
    INDEX
    Explanations

    structure-activity relationship

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

    This neuron identifies scientific phrases containing "structure-activity relationship" and related terminology in academic research.

    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_34/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
    違います
    -0.80
    デー
    -0.75
     programming
    -0.73
    acka
    -0.72
     submarines
    -0.71
    頂きました
    -0.71
    anya
    -0.71
     présentée
    -0.69
    ارب
    -0.69
    osomal
    -0.69
    POSITIVE LOGITS
     structure
    2.09
     Structure
    2.08
    Structure
    1.95
    structure
    1.81
     genotype
    1.69
     STRUCTURE
    1.63
    STRUCTURE
    1.53
     Correlation
    1.47
     correlation
    1.46
     relationship
    1.38
    Activations Density 0.131%

    No Known Activations