© 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. 10-GEMMASCOPE-RES-131K
    7. 14238
    Prev
    Next
    INDEX
    Explanations

    domestic animals

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

    references to domesticated animals and livestock.

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

    The neuron detects mentions of domestication, i.e. words and contexts referring to “domestic,” “domesticated,” or “domestication.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     they
    -1.92
    </h3>
    -1.23
    ra
    -1.17
    est
    -1.16
     contempl
    -1.16
     energe
    -1.13
     siquiera
    -1.11
    mobile
    -1.10
    の発
    -1.09
     estaban
    -1.09
    POSITIVE LOGITS
    jenigen
    1.66
    庒
    1.57
    pilih
    1.55
    τικού
    1.54
     Aktivität
    1.52
     feitos
    1.49
    Ꮞ
    1.48
    虽然
    1.48
    Recently
    1.45
    雖然
    1.45
    Activations Density 0.034%

    No Known Activations