© 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. 75440
    Prev
    Next
    INDEX
    Explanations

    Go package imports

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

    The neuron is most strongly activated by numeric literals in code.

    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
    summer
    -0.77
     summer
    -0.77
     Pur
    -0.75
    :][
    -0.75
    Summer
    -0.72
     格
    -0.71
    )=(
    -0.71
    ###########
    -0.69
    keo
    -0.69
    Johnson
    -0.68
    POSITIVE LOGITS
    reflect
    1.09
     fmt
    1.08
    fmt
    1.07
     reflect
    1.05
    strings
    0.94
    bytes
    0.93
     strings
    0.89
     refle
    0.89
    time
    0.88
     Reflect
    0.87
    Activations Density 0.056%

    No Known Activations