© 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. 34-GEMMASCOPE-RES-131K
    7. 103273
    Prev
    Next
    INDEX
    Explanations

    closing punctuation and code delimiters

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

    The neuron fires on structural code or document-section markers—i.e. keywords and identifiers that introduce blocks or declarations (e.g. “if”, “for”, XML tag names, CSS property names, “Court”, “v.”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ớ
    -0.91
    NSUserDefaults
    -0.82
     género
    -0.77
    MathML
    -0.76
     restricting
    -0.75
    看一下
    -0.74
     demonstrate
    -0.71
    🌓
    -0.71
     ...
    -0.70
    𝐛
    -0.69
    POSITIVE LOGITS
    ↵
    1.41
    0.77
    ,

    0.74
    Якщо
    0.74
    orap
    0.74
     facilement
    0.73
    Fu
    0.72
     saffron
    0.71
    SEN
    0.70
    Lin
    0.70
    Activations Density 0.052%
    No Known Activations