© 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. 22-GEMMASCOPE-RES-131K
    7. 68219
    Prev
    Next
    INDEX
    Explanations

    Q: / BSD License / Conversations (

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

    The neuron fires on uppercase technical labels and acronyms—especially programming‐language or format names like “BSD,” “C#,” or “ILAsm.”

    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
     their
    -1.52
    浓郁
    -1.18
     provide
    -1.17
     it
    -1.16
    鸯
    -1.14
     only
    -1.14
     Тек
    -1.13
     all
    -1.13
     phénom
    -1.11
     playera
    -1.11
    POSITIVE LOGITS
    Preparazione
    1.13
     instantiation
    1.13
    ējās
    1.13
     pescoço
    1.09
     unseres
    1.08
    知名
    1.06
     crescere
    1.05
     crescente
    1.05
    liche
    1.04
    oy
    1.03
    Activations Density 0.000%

    No Known Activations