© 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. 15888
    Prev
    Next
    INDEX
    Explanations

    programming code syntax and keywords

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

    The neuron is looking for loop or iteration constructs (e.g. “while,” stack‐based loops, index comparisons) in code.

    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
     explicou
    -1.05
     necesitan
    -0.98
     nélkül
    -0.91
     ។
    -0.87
    ні
    -0.87
     Kitchens
    -0.87
     verarbeitet
    -0.85
    jil
    -0.83
     ומש
    -0.82
     Sina
    -0.82
    POSITIVE LOGITS
     spp
    0.96
     trotz
    0.93
    spp
    0.86
    letoe
    0.83
    ViewImports
    0.82
    alucía
    0.81
    relief
    0.79
     دریا
    0.79
     suivants
    0.78
     rodo
    0.78
    Activations Density 0.000%

    No Known Activations