© 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. 70763
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific terms

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

    The neuron spikes on technical acronyms or jargon terms (especially uppercase sequences) marking domain-specific terminology.

    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
     myös
    -1.05
    なのかな
    -0.98
     lèvres
    -0.95
     mismas
    -0.94
    Honestly
    -0.93
    aną
    -0.93
    さんへ
    -0.90
    為に
    -0.90
     réunions
    -0.89
     soumettre
    -0.89
    POSITIVE LOGITS
    である
    1.32
     such
    1.05
     namely
    0.96
    それも
    0.95
     præ
    0.95
    名为
    0.90
    owska
    0.89
     شهرهای
    0.88
    で
    0.87
    auce
    0.86
    Activations Density 0.096%

    No Known Activations