© 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. 22-GEMMASCOPE-RES-131K
    7. 71722
    Prev
    Next
    INDEX
    Explanations

    class/function definitions

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

    The neuron is picking up on leading indentation (whitespace) tokens that mark the start of indented code lines.

    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
     two
    -1.12
     even
    -1.11
     from
    -1.05
     mutiara
    -1.02
    vább
    -1.02
     additional
    -1.00
    ternut
    -0.99
     Even
    -0.96
     components
    -0.93
     still
    -0.92
    POSITIVE LOGITS
     lorsqu
    1.03
     ambig
    1.02
     eerste
    0.98
     joyous
    0.95
     pierws
    0.94
    BrowserModule
    0.93
     coupes
    0.91
    oyer
    0.91
     Garnier
    0.91
     correcte
    0.90
    Activations Density 0.013%

    No Known Activations