© 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. 22-GEMMASCOPE-RES-131K
    7. 98657
    Prev
    Next
    INDEX
    Explanations

    animal welfare and harm

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

    content related to animal welfare, rights, and protection.

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

    The neuron activates on words referring to animals or animal‐related concepts (e.g. livestock, animals, animal welfare).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    z
    -1.52
    t
    -1.41
    for
    -1.41
    en
    -1.38
     like
    -1.38
    in
    -1.36
    b
    -1.32
     will
    -1.30
    w
    -1.26
    man
    -1.23
    POSITIVE LOGITS
    fokus
    1.77
    kalender
    1.70
    moderne
    1.62
    denk
    1.54
    denken
    1.54
    dekor
    1.53
     minimale
    1.53
    gelang
    1.52
     provinciale
    1.49
    klima
    1.48
    Activations Density 0.030%

    No Known Activations