© 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. 65757
    Prev
    Next
    INDEX
    Explanations

    URLs and code paths

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

    The neuron fires on URL patterns and hyperlink tokens (e.g. “https://…”, domain names, slashes).

    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
    netti
    -0.81
     confr
    -0.79
     Florentine
    -0.78
    uresh
    -0.77
     equipa
    -0.77
     nonstop
    -0.77
     carre
    -0.76
     wished
    -0.76
     ministro
    -0.75
    リーフ
    -0.75
    POSITIVE LOGITS
    leetcode
    0.97
     submissions
    0.91
     Difficulty
    0.90
    высо
    0.86
     Acceptance
    0.86
    提交
    0.83
    stdc
    0.83
     submitted
    0.82
    difficulty
    0.82
    niños
    0.82
    Activations Density 0.025%

    No Known Activations