© 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. 22-GEMMASCOPE-RES-131K
    7. 14786
    Prev
    Next
    INDEX
    Explanations

    code file headers

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

    The neuron activates on long runs of repeated punctuation characters (like “===”, “---”, or “–––––”) used as section dividers or separators in code comments.

    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
     với
    -1.09
     enregist
    -1.07
     удачи
    -1.06
    '
    -1.02
     красивые
    -0.99
    =
    -0.99
    {...
    -0.98
    睡
    -0.98
     hét
    -0.98
    kanak
    -0.97
    POSITIVE LOGITS
    これらの
    1.13
    ⁇
    1.09
    Artículos
    1.07
    Vastaa
    1.05
    Escrito
    1.05
    Donativos
    1.03
    īts
    1.00
    Подготовка
    1.00
    gemeester
    0.98
    iciado
    0.98
    Activations Density 0.011%

    No Known Activations