© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 115694
    Prev
    Next
    INDEX
    Explanations

    biological signals and communication

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

    scientific terminology related to cell signaling molecules and pathways.

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

    The neuron activates strongly on technical terms describing biological signaling and cell-to-cell communication molecules.

    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
    setContent
    -0.92
     thân
    -0.78
    eriksaan
    -0.76
    сар
    -0.75
    ดิ
    -0.73
    cab
    -0.72
    Tech
    -0.71
     Hampshire
    -0.69
    ociação
    -0.69
    Random
    -0.68
    POSITIVE LOGITS
     signals
    1.88
     signal
    1.87
     communication
    1.74
     signalling
    1.73
     signaling
    1.65
     messages
    1.47
     messengers
    1.44
     communicating
    1.42
    signal
    1.41
     messenger
    1.37
    Activations Density 0.302%

    No Known Activations