© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 90177
    Prev
    Next
    INDEX
    Explanations

    species and scientific names

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

    scientific names of species in taxonomy, particularly focusing on Latin binomial nomenclature for animals.

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

    The neuron strongly activates on numeric tokens (digits or multi‐digit numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     Australia
    -1.07
     Australian
    -1.04
     Brisbane
    -1.00
    Australia
    -0.91
     wolle
    -0.91
     Австра
    -0.84
     Queensland
    -0.82
    Australian
    -0.82
     استر
    -0.81
     Brazilian
    -0.80
    POSITIVE LOGITS
     Pallas
    1.12
     hibern
    0.95
     Fenn
    0.91
     hazel
    0.88
     Mongolia
    0.85
     Europese
    0.85
     Avrupa
    0.84
    Balk
    0.84
    alpine
    0.82
    Europe
    0.82
    Activations Density 0.094%

    No Known Activations