© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78129
    Prev
    Next
    INDEX
    Explanations

    ostrich and emu

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

    The neuron activates on Latin biological names, especially genus or genus-and-species terms in taxonomy.

    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
     caterpillar
    -0.78
    mousemove
    -0.76
     ryb
    -0.75
     Нужно
    -0.75
    CIF
    -0.75
    juh
    -0.74
     entrevistas
    -0.73
     squirrel
    -0.73
    香り
    -0.72
     fish
    -0.71
    POSITIVE LOGITS
     ostrich
    1.73
     emu
    1.48
     Ost
    1.17
     Rhea
    1.10
     Strut
    1.02
     turkey
    0.99
    Emu
    0.96
    Ost
    0.95
    emu
    0.94
     feathers
    0.90
    Activations Density 0.015%

    No Known Activations