© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129168
    Prev
    Next
    INDEX
    Explanations

    The neuron primarily activates on occurrences of the single-letter variable “l.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    'l' as identifier in code and math

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    玧
    -2.73
    茘
    -2.70
    
    -2.63
    
    -2.61
    ڧ
    -2.52
    鼙
    -2.50
    Existen
    -2.48
     จาก
    -2.47
    鋮
    -2.45
    鉝
    -2.36
    POSITIVE LOGITS
    \
    3.58
    ?"
    3.33
    ]
    3.06
     '
    3.02
    "
    2.75
    .,"
    2.58
    ?'
    2.47
    "'
    2.44
    !"
    2.38
     ,"
    2.38
    Activations Density 0.147%

    No Known Activations