© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 109371
    Prev
    Next
    INDEX
    Explanations

    Hindu Mahajana Sangam

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

    The neuron strongly activates on XML-style documentation comment markers (the “///” lines).

    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
     new
    -1.16
    nextProps
    -1.13
    więcej
    -1.10
    źródło
    -1.09
     ór
    -1.09
    zdjęcie
    -1.08
     exquisitely
    -1.02
     sitten
    -1.02
    espé
    -1.02
     varit
    -1.01
    POSITIVE LOGITS
     largely
    1.17
     quoc
    1.15
     procedimentos
    1.10
    wens
    1.04
     Ctr
    1.03
     …..
    1.03
     deterior
    1.02
     remarkably
    1.02
     predominantly
    1.00
     sooo
    0.99
    Activations Density 0.000%

    No Known Activations