© 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. 78940
    Prev
    Next
    INDEX
    Explanations

    animal release and captive management

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

    mentions of captive, bred, or managed wildlife and animal species.

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

    This neuron fires on explicit references to particular animal species (especially Latin binomials and common names) in a scientific or zoological context.

    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
     port
    -0.79
    滞在
    -0.76
     сель
    -0.76
    ⾏
    -0.73
    くだ
    -0.73
     cha
    -0.72
     Kay
    -0.71
     snake
    -0.71
    obiety
    -0.71
    进化
    -0.71
    POSITIVE LOGITS
     release
    1.70
    release
    1.59
     released
    1.58
     releases
    1.53
    Release
    1.46
     RELEASE
    1.39
     Releases
    1.35
     captive
    1.30
     Release
    1.27
    RELEASE
    1.27
    Activations Density 0.019%

    No Known Activations