© 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. 22-GEMMASCOPE-RES-131K
    7. 14857
    Prev
    Next
    INDEX
    Explanations

    get code or list

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

    This neuron fires on code‐block delimiters—especially the “{” that opens a block.

    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
     OFDb
    -0.88
    isional
    -0.82
    vun
    -0.81
    dai
    -0.80
     inp
    -0.80
    قال
    -0.79
    readLine
    -0.79
     Rück
    -0.78
    ceptar
    -0.77
     espíritu
    -0.77
    POSITIVE LOGITS
     information
    0.93
    伝え
    0.85
     leal
    0.81
     faithful
    0.79
     recent
    0.78
     provide
    0.77
     Approximation
    0.77
    外部連結
    0.75
     explaining
    0.75
     stale
    0.75
    Activations Density 0.038%

    No Known Activations