© 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. 67945
    Prev
    Next
    INDEX
    Explanations

    programming structures

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

    The neuron fires on runs of leading whitespace (indentation) in XML/markup documents.

    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
     it
    -1.16
     on
    -1.03
     if
    -1.02
     their
    -0.97
    calips
    -0.92
    entrant
    -0.92
    に挑戦
    -0.91
    $,
    
    -0.91
     Those
    -0.90
    rebbero
    -0.90
    POSITIVE LOGITS
    alny
    1.14
     weihnachten
    1.13
    Israël
    1.05
     нашим
    1.01
    Vra
    1.01
     verborgen
    1.00
    ajout
    0.98
     befes
    0.98
    Algérie
    0.98
    Capacidad
    0.97
    Activations Density 0.001%

    No Known Activations