© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 66668
    Prev
    Next
    INDEX
    Explanations

    templating language syntax

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

    This neuron detects templating/interpolation markers (e.g. “{{”, “<%=”, “{%”, “$…”) 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
    camisa
    -1.09
    tá
    -1.07
    しくは
    -1.05
    PostId
    -0.99
    しましたが
    -0.98
    っけ
    -0.97
    Groet
    -0.95
    Desperate
    -0.94
    mær
    -0.90
    aceite
    -0.90
    POSITIVE LOGITS
    S
    1.07
    ру
    1.06
     "'
    1.05
    
    1.05
     also
    1.04
    也
    1.03
    µ
    1.03
    cy
    1.02
    L
    1.02
    X
    1.01
    Activations Density 0.014%

    No Known Activations