© 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. 34-GEMMASCOPE-RES-131K
    7. 803
    Prev
    Next
    INDEX
    Explanations

    animal and subsequent terms

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

    references to animals, particularly in scientific or legal contexts.

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

    The neuron activates on the word “animal” (in any form or compound).

    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
     dino
    -0.97
    Paquete
    -0.93
     compli
    -0.93
     cheio
    -0.92
     Mengh
    -0.87
     hobbit
    -0.87
     koi
    -0.87
     asa
    -0.85
    Advert
    -0.85
    ÑO
    -0.84
    POSITIVE LOGITS
     kingdom
    1.42
     husbandry
    1.34
     welfare
    1.30
    cules
    1.22
    cule
    1.21
    istic
    1.17
     Kingdom
    1.08
     crackers
    1.06
     shelters
    1.06
     Animal
    1.05
    Activations Density 0.035%

    No Known Activations