© 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. 10-GEMMASCOPE-RES-131K
    7. 20315
    Prev
    Next
    INDEX
    Explanations

    template code syntax

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

    The neuron consistently fires on occurrences of the literal word “template” (e.g. in code or markup).

    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
    s
    -2.78
    鐿
    -2.69
     dejected
    -2.50
    岀
    -2.42
    }
    -2.36
    みてください
    -2.34
    𞤤
    -2.27
    }$
    -2.27
    se
    -2.25
     aficionados
    -2.22
    POSITIVE LOGITS
    Ⲉ
    2.70
    昻
    2.67
    靺
    2.59
    𓆜
    2.50
    i
    2.50
    ↵
    2.45
    퐹
    2.45
    ſelves
    2.42
    ちゃんは
    2.41
    ༑
    2.38
    Activations Density 0.011%

    No Known Activations