© 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. 79660
    Prev
    Next
    INDEX
    Explanations

    issue, matter, problem, topic

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

    The neuron strongly activates on occurrences of the word “issue.”

    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
    anggap
    -1.02
    Viitteet
    -0.97
    方式
    -0.95
    vindo
    -0.94
     bằng
    -0.93
     folgte
    -0.90
    jaket
    -0.90
     τρό
    -0.89
    ='$
    -0.88
     capabilities
    -0.88
    POSITIVE LOGITS
     discussed
    1.30
     matter
    1.15
     concerns
    1.13
     discussion
    1.13
     topic
    1.10
     debated
    1.10
     issue
    1.09
     concern
    1.09
     matters
    1.08
     vấn
    1.08
    Activations Density 0.047%

    No Known Activations