© 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. 90532
    Prev
    Next
    INDEX
    Explanations

    map, rules, USA, Tag

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

    The neuron fires on occurrences of the Buddhist term “dharma”/“dhamma” (e.g. in titles like Dhammapada or Abhidharma).

    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
    ób
    -0.82
    HOM
    -0.78
     पू
    -0.75
    ﴾
    -0.74
     DHL
    -0.71
    扒
    -0.71
    TypeOf
    -0.71
     deaktiviert
    -0.69
    ințe
    -0.67
     πρω
    -0.67
    POSITIVE LOGITS
    τές
    0.77
     næste
    0.75
     decisões
    0.73
     REPORTER
    0.72
     bombing
    0.72
     batas
    0.72
     Anreg
    0.71
     implementations
    0.71
     Announcements
    0.71
     array
    0.70
    Activations Density 0.007%

    No Known Activations