© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12730
    Prev
    Next
    INDEX
    Explanations

    code and technical terms

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

    The neuron is keyed to Python code constructs—especially occurrences of “self” and “return” (and related method‐definition tokens) in code 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
     desmotiv
    -1.17
     seite
    -1.07
     Matéri
    -1.05
    काश
    -1.03
     hintergrund
    -1.02
     Questo
    -1.02
    maiden
    -1.00
     scipy
    -0.98
     AQUÍ
    -0.96
     türkiye
    -0.96
    POSITIVE LOGITS
     of
    1.55
     name
    1.07
     gets
    0.96
     creating
    0.94
    ERK
    0.93
    ῾
    0.90
     mối
    0.90
    ֖
    0.90
     referirse
    0.90
     wary
    0.88
    Activations Density 0.003%

    No Known Activations