© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108956
    Prev
    Next
    INDEX
    Explanations

    brood and bees

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

    biological and entomological terms related to insects, particularly bees, wasps, and other arthropods.

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

    The neuron is triggered by tokens containing underscores (e.g. API_bot, BW_API_bot identifiers).

    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
    kingdom
    -0.86
    jetty
    -0.75
    衛門
    -0.73
     Symphon
    -0.73
     Haush
    -0.69
    thickness
    -0.69
    μερα
    -0.69
     companyId
    -0.67
    ználat
    -0.67
    Simpson
    -0.67
    POSITIVE LOGITS
     brood
    1.09
     Brood
    0.98
     SC
    0.86
    Minerals
    0.85
     Zer
    0.84
    Ling
    0.76
     Ling
    0.75
     minerals
    0.75
    brood
    0.75
    Zer
    0.74
    Activations Density 0.015%

    No Known Activations