© 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. 33583
    Prev
    Next
    INDEX
    Explanations

    control flow and variable names

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

    The neuron fires on programming‐language tokens (identifiers, symbols, and operators embedded 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
     their
    -1.56
     While
    -1.12
    
    -1.08
    kuli
    -1.07
     other
    -1.05
    JSONArray
    -1.03
    ladı
    -1.03
    ográfico
    -1.02
     Menggunakan
    -1.00
     coloridas
    -0.99
    POSITIVE LOGITS
    5
    1.04
    2
    0.96
     """
    0.94
    underbrace
    0.93
     desierto
    0.93
    梶
    0.92
    榊
    0.91
     оказалось
    0.90
    どこに
    0.90
    怼
    0.90
    Activations Density 0.050%

    No Known Activations