Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8636
    Prev
    Next
    INDEX
    Explanations

    subspecies names

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

    scientific species names, particularly the Latin 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_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
     crap
    -0.74
    держка
    -0.71
     Will
    -0.71
    jMenu
    -0.71
    了很多
    -0.70
    []={
    -0.70
     erstellt
    -0.69
     repeating
    -0.69
     Or
    -0.69
     species
    -0.68
    POSITIVE LOGITS
     subspecies
    1.67
     nominate
    1.16
    nomin
    0.98
     Nomin
    0.90
     ssp
    0.84
    Emoji
    0.84
     Livro
    0.81
     номина
    0.81
     Viti
    0.81
    Vous
    0.80
    Activations Density 0.067%

    No Known Activations