© 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. 34-GEMMASCOPE-RES-131K
    7. 77494
    Prev
    Next
    INDEX
    Explanations

    `documentation summaries and comments`

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

    The neuron specializes in spotting code‐comment and documentation markup tokens—especially XML/HTML‐style doc tags (e.g. “<”, “>”, “para”, “devdoc”) and comment/copyright markers.

    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
    接近
    -0.77
    即使
    -0.75
    塗
    -0.73
     фильм
    -0.72
    连续
    -0.72
    TagHelpers
    -0.71
     AIC
    -0.70
    可能
    -0.70
     ideolog
    -0.69
     ließ
    -0.69
    POSITIVE LOGITS
     remarks
    1.20
    Remarks
    0.81
     comments
    0.80
     partículas
    0.80
    votes
    0.80
    ይ
    0.80
    ამ
    0.78
     wise
    0.77
     Como
    0.76
    ceaux
    0.76
    Activations Density 0.020%

    No Known Activations