© 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. 60099
    Prev
    Next
    INDEX
    Explanations

    animal names, taxonomic terms

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

    names of birds of prey, predators, and insects.

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

    The neuron fires on names of predatory birds (raptors).

    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
    '
    -1.72
     髪
    -1.57
    结局
    -1.48
     Artículo
    -1.46
    ,"
    -1.46
    </h1>
    -1.45
    
    -1.42
    ️
    -1.41
    ısında
    -1.36
    ,
    -1.34
    POSITIVE LOGITS
     our
    1.52
    🢒
    1.50
    Bukan
    1.47
    6
    1.40
    Mereka
    1.38
    俛
    1.38
     verbringen
    1.34
    Sebelumnya
    1.34
    がありますが
    1.32
    Sudah
    1.30
    Activations Density 0.077%

    No Known Activations