© 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. 48662
    Prev
    Next
    INDEX
    Explanations

    moths and their families

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

    moths and taxonomic classifications in scientific text.

    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
     Eze
    -0.83
    Eze
    -0.79
     गर्
    -0.79
     alliance
    -0.79
    OrNil
    -0.75
     rodilla
    -0.75
     wireless
    -0.74
    ълга
    -0.71
     curing
    -0.71
    ฟ้า
    -0.69
    POSITIVE LOGITS
     moths
    2.59
     moth
    2.42
     butterflies
    1.88
     butterfly
    1.86
     Moth
    1.84
     Butterflies
    1.69
    moth
    1.66
     caterpillar
    1.61
     Butterfly
    1.60
     caterpillars
    1.59
    Activations Density 0.125%

    No Known Activations