© 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. 34607
    Prev
    Next
    INDEX
    Explanations

    code constructs like objects and variables

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

    This neuron fires on programming code segments, identifying lines of source‐code syntax rather than natural language.

    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
     incluso
    -1.02
    ihnachts
    -0.98
    epsfig
    -0.97
    iferous
    -0.96
    麓
    -0.95
     even
    -0.91
     whatever
    -0.90
    攫
    -0.89
     плата
    -0.88
    揶
    -0.88
    POSITIVE LOGITS
    他們的
    1.04
    ้อน
    1.00
     вони
    0.95
    我們的
    0.93
    他们的
    0.91
     kerül
    0.91
    zensionen
    0.90
     naszego
    0.88
     باشند
    0.87
     שלנו
    0.87
    Activations Density 0.015%

    No Known Activations