© 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. 10-GEMMASCOPE-RES-131K
    7. 101439
    Prev
    Next
    INDEX
    Explanations

    animal and plant names

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

    Latin-derived species names and taxonomic classifications.

    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
    TRIBUTES
    -1.41
    PURE
    -1.38
     ambiti
    -1.38
     qualif
    -1.36
     impec
    -1.36
    Smarty
    -1.36
     weder
    -1.34
     espac
    -1.34
     چوبی
    -1.34
     milliers
    -1.34
    POSITIVE LOGITS
     that
    1.67
     often
    1.55
     usually
    1.54
     обычно
    1.54
     only
    1.52
     one
    1.48
     Sometimes
    1.44
     Usually
    1.42
     sometimes
    1.41
     probably
    1.38
    Activations Density 0.195%

    No Known Activations