© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30152
    Prev
    Next
    INDEX
    Explanations

    animals and wildlife

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

    This neuron identifies phrases describing relationships between animals and their environments, particularly focusing on wildlife, dangerous animals, and their interactions with humans.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered by @neilrathi
    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
    Negative Logits
     köpek
    -0.85
    Aliases
    -0.80
     Bulldog
    -0.79
     Bulldogs
    -0.77
    SMTP
    -0.75
    ném
    -0.74
     Pseudomonas
    -0.74
    ḵ
    -0.74
     mennes
    -0.73
     capacitors
    -0.69
    POSITIVE LOGITS
     animals
    4.91
     animal
    4.00
     Animals
    3.38
    animals
    3.20
    animal
    3.19
    Animals
    3.05
     Animal
    2.97
     animales
    2.92
    動物
    2.91
    Animal
    2.73
    Activations Density 0.120%

    No Known Activations