© 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. 10-GEMMASCOPE-RES-131K
    7. 60824
    Prev
    Next
    INDEX
    Explanations

    species description and distribution

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

    This neuron identifies passages describing taxonomic classifications, particularly for species of moths, butterflies, and other animals, with strong activations for scientific descriptions.

    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_10/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
    着一个
    -1.66
     inalámbrica
    -1.65
    了两
    -1.63
    了些
    -1.52
    施展
    -1.48
     silnika
    -1.46
     erity
    -1.44
    が終わ
    -1.44
     jälkeen
    -1.44
     siyang
    -1.40
    POSITIVE LOGITS
     but
    1.56
    Bardzo
    1.50
    Опис
    1.50
     ")");
    1.48
     utilizzare
    1.48
     considerare
    1.45
     utenti
    1.45
    Etimología
    1.45
    Etimo
    1.44
    ១
    1.41
    Activations Density 0.167%

    No Known Activations