© 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. 34-GEMMASCOPE-RES-131K
    7. 883
    Prev
    Next
    INDEX
    Explanations

    gene or enzyme family

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

    The neuron detects technical or academic content discussing components, specifications, or features of systems, particularly when describing properties or characteristics of entities.

    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
    ⡏
    -0.79
    Wirtschaft
    -0.77
     visas
    -0.77
    டம்
    -0.75
     стрем
    -0.75
    Langue
    -0.74
    एं
    -0.73
    Mnemonic
    -0.72
    Filtro
    -0.71
     данной
    -0.71
    POSITIVE LOGITS
     ingredient
    1.16
     symptom
    1.00
     gene
    0.98
     cytokine
    0.94
     creditor
    0.91
     enzyme
    0.91
    ConstraintSet
    0.90
     Ingredient
    0.86
     extensive
    0.85
     hormone
    0.85
    Activations Density 0.214%

    No Known Activations