© 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. 49272
    Prev
    Next
    INDEX
    Explanations

    systems biology topics and mechanisms

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

    scientific or academic review content focused on specific fields like biology, medicine, or neuroscience.

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

    The neuron fires on high-level academic or technical field terms—especially biology-related discipline names and research-topic keywords.

    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
     even
    -1.77
     unless
    -1.51
     if
    -1.48
     just
    -1.41
     like
    -1.39
     because
    -1.37
     every
    -1.34
     isn
    -1.32
     doesn
    -1.32
     certainly
    -1.31
    POSITIVE LOGITS
    particularly
    2.00
    以及
    1.88
    及其
    1.87
    specifically
    1.86
    Specifically
    1.68
     både
    1.64
    especially
    1.61
    特に
    1.58
    ocusing
    1.55
    尤其是
    1.52
    Activations Density 0.565%

    No Known Activations