© 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. 91831
    Prev
    Next
    INDEX
    Explanations

    breeding and parents

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

    scientific or technical text about plant breeding, genetics, and agricultural varieties.

    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
     screened
    -0.91
     Screening
    -0.85
     screening
    -0.84
     pantalla
    -0.84
    CHANNELS
    -0.83
    creen
    -0.79
    zigen
    -0.77
    ठ
    -0.77
    (${
    -0.76
    nější
    -0.75
    POSITIVE LOGITS
     cytoplasmic
    1.15
     parental
    1.05
     parent
    1.01
     cytoplas
    0.99
     parents
    0.99
     Line
    0.91
     Parent
    0.90
     male
    0.88
    PARENT
    0.85
    parent
    0.82
    Activations Density 0.053%

    No Known Activations