© 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. 64167
    Prev
    Next
    INDEX
    Explanations

    illegal wildlife trade

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

    content related to endangered wildlife and conservation, particularly about rhinos, tigers, and illegal wildlife trading.

    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
    allowNull
    -0.84
    onoma
    -0.79
     rabbits
    -0.79
     pigs
    -0.78
     Gass
    -0.77
    äß
    -0.75
    EMERGENCY
    -0.74
     chickens
    -0.73
     engineers
    -0.73
     conejo
    -0.72
    POSITIVE LOGITS
     CITES
    2.05
     ivory
    1.52
     TRAFFIC
    1.45
    Illegal
    1.35
     illegal
    1.19
    Wildlife
    1.18
     wildlife
    1.15
     Ivory
    1.15
     Illegal
    1.12
    ivory
    1.12
    Activations Density 0.021%

    No Known Activations