© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108930
    Prev
    Next
    INDEX
    Explanations

    representatives of species

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

    scientific descriptions of animal species.

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

    The neuron strongly activates on scientific Latin names (genus and species terms) in taxonomic or biological contexts.

    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
     quả
    -0.79
    gendes
    -0.79
    もいい
    -0.79
     peaks
    -0.78
     and
    -0.78
     novel
    -0.78
    餓
    -0.77
    른
    -0.76
    妈
    -0.76
     procedure
    -0.76
    POSITIVE LOGITS
     representatives
    1.34
     représentants
    1.20
     Representatives
    1.02
    Representatives
    1.02
    represent
    1.01
     representantes
    0.96
    多年
    0.92
     cukru
    0.88
     REPRESENTATIVES
    0.88
     וג
    0.84
    Activations Density 0.016%

    No Known Activations