© 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. 34-GEMMASCOPE-RES-131K
    7. 32389
    Prev
    Next
    INDEX
    Explanations

    zip and compression files

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

    The neuron fires on programming‐related tokens having to do with file compression—e.g. “zip,” “files,” “contains,” “with,” and code symbols like “#include” or “define” —so it’s spotting source‐code contexts about handling zip files.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ﻤ
    -0.78
    剑
    -0.74
    觀眾
    -0.74
    તી
    -0.72
     جلسه
    -0.71
    掾
    -0.70
     汉
    -0.68
    umpulan
    -0.68
    劍
    -0.68
    ('.')
    -0.67
    POSITIVE LOGITS
     Zip
    0.96
     Central
    0.82
    zido
    0.80
    itoare
    0.75
    中央
    0.75
    jzen
    0.74
     zip
    0.73
     comment
    0.73
    âu
    0.73
     Todes
    0.73
    Activations Density 0.020%

    No Known Activations