© 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. 10-GEMMASCOPE-RES-131K
    4. 69020
    Prev
    Next
    INDEX
    Explanations

    CloudFormation template structure

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

    The neuron strongly activates on code or text referring to cloud‐infrastructure templates—especially AWS “CloudFormation” and related template keywords.

    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
    <bos>
    -1.91
    。
    -1.83
     sendok
    -1.59
     Meldung
    -1.48
     económicas
    -1.45
     trovo
    -1.42
     After
    -1.41
     electrónico
    -1.41
    ()
    -1.40
    is
    -1.36
    POSITIVE LOGITS
     コレクション
    1.41
     documental
    1.41
     previo
    1.39
     propi
    1.38
    )”
    1.38
     infan
    1.38
    ]");
    1.37
    )");
    1.33
    (");
    1.32
    уза
    1.28
    Activations Density 0.014%

    No Known Activations