© 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. 22-GEMMASCOPE-RES-131K
    4. 130640
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on specialized content nouns, especially technical or domain-specific terms in scientific or professional contexts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    how many

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Some
    -0.97
    +="
    -0.96
     greifen
    -0.94
     tanques
    -0.94
     bật
    -0.94
     some
    -0.93
    いろいろ
    -0.91
    همچنین
    -0.91
    兩個
    -0.90
    tovat
    -0.90
    POSITIVE LOGITS
     than
    1.64
     available
    1.08
     najdete
    1.02
    リエーション
    0.94
     in
    0.94
     تعداد
    0.88
    霎
    0.88
    weeted
    0.87
     to
    0.85
    ournal
    0.85
    Activations Density 0.097%

    No Known Activations