© 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. 93273
    Prev
    Next
    INDEX
    Explanations

    numerical sequences and contexts

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

    The neuron specializes in spotting mentions of specific scientific methods or techniques (e.g. “yeast two-hybrid screening,” “CMB lensing maps,” “traditional two-point statistics”).

    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
     nogle
    -0.79
    Arsenal
    -0.78
     Berikut
    -0.77
     guessed
    -0.73
    ⚾
    -0.72
    ///**
    -0.69
    Collection
    -0.68
    ']")
    -0.66
    IEEE
    -0.65
    DataItem
    -0.65
    POSITIVE LOGITS
    point
    1.56
     point
    1.48
     Two
    1.38
    Two
    1.34
     Point
    1.25
     twos
    1.22
    Point
    1.21
    Three
    1.12
     Three
    1.12
    two
    1.11
    Activations Density 0.055%

    No Known Activations