© 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. 58113
    Prev
    Next
    INDEX
    Explanations

    exotic animals or pets

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

    This neuron responds to mentions of animals and related creature terms (e.g. species or pet names).

    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
     consistency
    -0.95
    Whale
    -0.88
     जाता
    -0.82
     whale
    -0.80
    鲸
    -0.78
     logos
    -0.78
    ән
    -0.77
     moose
    -0.76
     giraffe
    -0.76
     Whale
    -0.75
    POSITIVE LOGITS
     exotic
    1.48
    exotic
    1.28
     aquarium
    1.21
     Exotic
    1.17
     exo
    1.16
     snakes
    1.15
    Exotic
    1.13
     goldfish
    1.11
    snake
    1.05
     guinea
    1.05
    Activations Density 0.027%

    No Known Activations