© 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. 93616
    Prev
    Next
    INDEX
    Explanations

    PI3K pathway

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

    The neuron detects the biochemical signaling pathway "PI3K" (phosphoinositide 3-kinase) in scientific texts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     particularly
    -0.77
     間
    -0.77
     appealing
    -0.77
    ↵↵
    -0.75
     żyw
    -0.75
    0
    -0.72
    7
    -0.71
    babel
    -0.70
     chociaż
    -0.69
    1
    -0.69
    POSITIVE LOGITS
     pij
    0.97
    genomen
    0.92
    ेंद
    0.90
     ............
    0.89
    faccia
    0.88
     pios
    0.87
    ucap
    0.87
    Gim
    0.86
    rdquo
    0.86
    piro
    0.84
    Activations Density 0.054%

    No Known Activations