© 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. 10-GEMMASCOPE-RES-131K
    7. 74195
    Prev
    Next
    INDEX
    Explanations

    bird, insect, or scientific names

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

    The neuron strongly activates on taxonomic names—Latin genus, species, and family terms (e.g. Sphingidae, rufous, flycatcher).

    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
    ureusement
    -1.76
     эле
    -1.67
    菝
    -1.59
    萏
    -1.52
    ığı
    -1.46
    ‚
    -1.46
     maroon
    -1.46
    ев
    -1.45
     lament
    -1.44
     Jego
    -1.43
    POSITIVE LOGITS
     that
    1.60
    AÇÃO
    1.60
    鵟
    1.58
    踮
    1.54
     the
    1.54
    棡
    1.49
    ,—
    1.45
     geschlagen
    1.44
     altes
    1.40
    秣
    1.38
    Activations Density 0.009%

    No Known Activations