© 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. 72664
    Prev
    Next
    INDEX
    Explanations

    programming code declarations

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

    The neuron fires on code identifiers (variable or object names) in programming snippets.

    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
    參加
    -0.99
    ὔ
    -0.97
    りゃ
    -0.94
     nombreuses
    -0.88
    楽しめます
    -0.85
    gridColumn
    -0.85
     Fußballspieler
    -0.85
    FTFY
    -0.84
    口气
    -0.84
    捗
    -0.82
    POSITIVE LOGITS
     réfugi
    1.00
    ६
    1.00
     époux
    0.96
     szeret
    0.95
     szüks
    0.93
    kanı
    0.93
    śred
    0.92
    пь
    0.91
    gemäß
    0.90
     vrijdag
    0.89
    Activations Density 0.010%

    No Known Activations