© 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. 93581
    Prev
    Next
    INDEX
    Explanations

    animals and creatures

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

    mentions of animals in ecological or biological contexts.

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

    The neuron strongly activates on words referring to living beings—especially animals or creatures.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     involving
    -0.97
     aimed
    -0.94
    licópter
    -0.94
     vettor
    -0.93
     woman
    -0.91
     soddis
    -0.90
     aufgestellt
    -0.88
     étant
    -0.84
     senjata
    -0.82
     kişinin
    -0.82
    POSITIVE LOGITS
     who
    1.60
     animals
    1.28
     whom
    1.20
     critters
    1.19
     species
    1.13
     suiker
    1.09
     whose
    1.09
    animals
    1.07
     roaming
    1.00
     that
    0.99
    Activations Density 0.046%

    No Known Activations