© 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. 64997
    Prev
    Next
    INDEX
    Explanations

    research reports

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

    This neuron detects technical numerical expressions and mathematical range statements (e.g. “[1..N+1]” or phrases like “which means” in algorithm descriptions).

    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
    Toolbox
    -0.75
    ото
    -0.72
    allen
    -0.69
     Zack
    -0.67
     itong
    -0.65
     Tools
    -0.65
    okan
    -0.64
    ✶
    -0.63
    zb
    -0.63
     Hause
    -0.62
    POSITIVE LOGITS
     συν
    0.72
    ibley
    0.70
     discs
    0.69
     disks
    0.68
     resistivity
    0.66
    atisk
    0.65
    Continent
    0.64
    hma
    0.64
     intval
    0.64
     combate
    0.64
    Activations Density 0.058%

    No Known Activations