© 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. 10-GEMMASCOPE-RES-131K
    7. 86253
    Prev
    Next
    INDEX
    Explanations

    template expressions

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

    This neuron detects the endings of template control blocks—e.g. Jinja/Django “{% … %}” closing tags such as `{% endif %}` or `{% endfor %}`.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     žen
    -1.77
    AppComponent
    -1.62
     john
    -1.59
     tomto
    -1.59
    ÍN
    -1.57
    趼
    -1.51
     takimi
    -1.51
    toDouble
    -1.50
    PAIGN
    -1.48
     oraz
    -1.47
    POSITIVE LOGITS
    u
    1.76
    5
    1.66
    。　　
    1.64
    0
    1.64
    y
    1.63
    c
    1.55
    k
    1.52
     before
    1.51
    ;
    1.48
    ed
    1.48
    Activations Density 0.002%

    No Known Activations