© 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. 22-GEMMASCOPE-RES-131K
    7. 73542
    Prev
    Next
    INDEX
    Explanations

    code closing characters

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

    The neuron fires on occurrences of “url” (including capitalized “Url”) and related URL‐handling tokens in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     Caller
    -1.00
    stot
    -0.96
     выбор
    -0.91
     вашей
    -0.91
    onix
    -0.88
    koning
    -0.86
    VISIONS
    -0.85
    îne
    -0.84
    ubic
    -0.83
     quando
    -0.82
    POSITIVE LOGITS
    eternal
    0.98
     }}$}
    0.90
     STER
    0.89
    commentId
    0.88
     site
    0.88
     EXTER
    0.88
     URL
    0.88
    BeginInit
    0.88
    🫰
    0.87
     urls
    0.86
    Activations Density 0.051%

    No Known Activations