© 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. 10-GEMMASCOPE-RES-131K
    7. 110844
    Prev
    Next
    INDEX
    Explanations

    animals and nature terms

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

    This neuron detects names of insects and arthropods like grasshopper, cricket, mantis, hopper, and related biological classification terms.

    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
    陆续
    -1.91
    唻
    -1.88
     polish
    -1.86
    婊
    -1.83
     arou
    -1.83
    并未
    -1.80
    上げる
    -1.80
     banish
    -1.78
     fleeting
    -1.77
    嘥
    -1.77
    POSITIVE LOGITS
    n
    2.30
    k
    2.13
     szary
    2.11
    '
    2.09
    0
    2.03
    m
    1.88
    凩
    1.87
     białym
    1.80
    堙
    1.80
    獁
    1.79
    Activations Density 0.004%

    No Known Activations