© 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. 112344
    Prev
    Next
    INDEX
    Explanations

    scientific species names

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

    scientific Latin names of species in biological research.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron detects Latin scientific taxonomy names (e.g. genus and species or family names).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     your
    -2.55
     will
    -2.31
     like
    -1.97
     with
    -1.96
     or
    -1.90
     now
    -1.88
     on
    -1.86
     out
    -1.83
     by
    -1.77
     as
    -1.66
    POSITIVE LOGITS
     lorsqu
    2.13
     étan
    1.67
     réfrig
    1.60
     lorsque
    1.59
     discours
    1.59
     humeur
    1.56
    琑
    1.55
    joyed
    1.54
     länder
    1.50
     kontroli
    1.50
    Activations Density 0.167%

    No Known Activations