© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15274
    Prev
    Next
    INDEX
    Explanations

    accessing html attributes

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

    The neuron detects numeric literals used as attribute values in code snippets (e.g. IDs, href or data-attribute numbers).

    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
    FORME
    -1.42
     được
    -1.41
     souvent
    -1.40
    秾
    -1.39
     resistente
    -1.37
    罍
    -1.36
     icône
    -1.35
     requiere
    -1.34
     recently
    -1.31
    ünd
    -1.31
    POSITIVE LOGITS
     while
    2.13
    ,
    1.89
     because
    1.88
     before
    1.80
     in
    1.77
     with
    1.75
     by
    1.66
     or
    1.65
     than
    1.64
    gencias
    1.64
    Activations Density 0.005%

    No Known Activations