© 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. 14539
    Prev
    Next
    INDEX
    Explanations

    Streptomyces species names

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

    scientific and organizational names, particularly bacteria like "Streptomyces" and publication/media entities.

    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
     réjou
    -1.81
    ло
    -1.75
     THERE
    -1.74
    та
    -1.72
     creativo
    -1.63
    啶
    -1.62
     SUCH
    -1.62
    р
    -1.59
     Tried
    -1.58
     EXCELL
    -1.58
    POSITIVE LOGITS
     other
    2.28
    他的
    1.72
     their
    1.72
    每个
    1.66
     these
    1.59
     також
    1.59
     أيض
    1.59
     prenotazione
    1.59
     каждом
    1.52
     both
    1.51
    Activations Density 0.001%

    No Known Activations