© 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. 64963
    Prev
    Next
    INDEX
    Explanations

    arg, ¶, Sometimes, How, Cop

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

    This neuron activates on code identifiers—particularly argument names like “arg” in code snippets.

    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
     even
    -1.22
     almost
    -0.95
     innumerable
    -0.94
     with
    -0.93
     during
    -0.92
     three
    -0.89
     fourteen
    -0.87
     through
    -0.86
     undeniably
    -0.86
     at
    -0.85
    POSITIVE LOGITS
     сохра
    1.01
     somente
    0.96
    hman
    0.94
     procedimientos
    0.90
     turmoil
    0.88
     continually
    0.86
    ____
    0.86
     WIL
    0.85
    踯
    0.85
     Arg
    0.83
    Activations Density 0.000%

    No Known Activations