© 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. 54182
    Prev
    Next
    INDEX
    Explanations

    pathway activation

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

    molecular signaling pathways in cellular biology, particularly those involving protein kinases and transcription factors.

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

    The neuron specializes in picking out mentions of molecular signaling pathways and their activation descriptors.

    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
     response
    -0.84
    ЧЕСКИ
    -0.83
    Семья
    -0.81
     由
    -0.80
     fiabilité
    -0.79
     vzor
    -0.77
     জন
    -0.75
     fortemente
    -0.75
    踏
    -0.75
    Objetivo
    -0.75
    POSITIVE LOGITS
     DateFormat
    0.83
    arsk
    0.77
     nitric
    0.76
    \-
    0.76
    conditioning
    0.75
    ectin
    0.75
     cá
    0.74
    IMENTO
    0.72
    在于
    0.72
     chivalry
    0.71
    Activations Density 0.470%

    No Known Activations