© 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. 34512
    Prev
    Next
    INDEX
    Explanations

    extended, ext3, file extensions, extcon, extents, ExtUtils

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

    The neuron fires on occurrences of the substring “ext,” such as in file‐ or namespace‐extension identifiers.

    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
     сможет
    -2.34
    万物
    -2.09
    踽
    -2.08
     numeros
    -2.03
     笔画
    -2.00
     adhering
    -1.97
    }$
    -1.97
    
    -1.94
     processo
    -1.92
     elet
    -1.91
    POSITIVE LOGITS
     '
    2.94
    t
    2.92
    3
    2.61
    4
    2.55
     esimer
    2.50
     amiable
    2.50
     impoverished
    2.47
    9
    2.44
    一個
    2.36
     crowning
    2.36
    Activations Density 0.012%

    No Known Activations