© 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. 71210
    Prev
    Next
    INDEX
    Explanations

    code structure delimiters

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

    The neuron fires on programming‐language syntax and identifiers—e.g. braces, colons, keywords, and capitalized type/class names.

    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
     étui
    -1.02
    alucía
    -1.02
    iconCls
    -1.01
     calça
    -0.98
     baumwolle
    -0.98
     fiable
    -0.95
    Vin
    -0.95
     MATTER
    -0.94
     tvo
    -0.93
     dezelve
    -0.93
    POSITIVE LOGITS
     or
    1.19
     вместо
    1.16
     instead
    1.11
    另一种
    1.06
     but
    1.00
    むしろ
    1.00
    普通的
    0.93
     from
    0.91
    プレミアム
    0.88
     rudimentary
    0.87
    Activations Density 0.003%

    No Known Activations