© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 93016
    Prev
    Next
    INDEX
    Explanations

    drive-thru restaurant

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

    The neuron fires on code‐level identifiers—particularly imported package names, module or library names, and annotation labels.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     your
    -0.97
    aglia
    -0.97
    🧿
    -0.96
    NRAS
    -0.94
    霎
    -0.92
    npj
    -0.91
    boiling
    -0.90
    graham
    -0.90
     развития
    -0.89
    rugby
    -0.88
    POSITIVE LOGITS
    There
    1.21
    right
    0.99
    It
    0.97
    However
    0.96
     tecniche
    0.91
    size
    0.91
     appassion
    0.91
    low
    0.91
     trover
    0.91
     generell
    0.90
    Activations Density 0.000%

    No Known Activations