© 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. 58545
    Prev
    Next
    INDEX
    Explanations

    animal and wildlife

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

    content related to wildlife, animals, and artwork featuring animals.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     bateaux
    -0.85
    cobs
    -0.85
     zombies
    -0.84
     Tomatoes
    -0.83
    鸠
    -0.76
     DOLL
    -0.73
    鍛
    -0.73
     Worms
    -0.73
    Ḍ
    -0.72
    渔
    -0.71
    POSITIVE LOGITS
     animal
    3.53
     animals
    3.48
    animal
    2.88
     Animal
    2.67
    Animal
    2.63
     wildlife
    2.55
     zoo
    2.48
    animals
    2.48
     Animals
    2.41
    Animals
    2.41
    Activations Density 0.127%

    No Known Activations