© 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. 71528
    Prev
    Next
    INDEX
    Explanations

    sequences after specific words

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

    The neuron strongly activates on the word “generation,” including when it appears within a hyphenated form like “next-generation.”

    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
    Каждый
    -1.06
     vectoriales
    -0.91
    wenden
    -0.88
    Электро
    -0.88
     köy
    -0.87
    Largeur
    -0.87
    helfen
    -0.86
     Permite
    -0.85
    источник
    -0.85
    ೭
    -0.85
    POSITIVE LOGITS
     primarily
    0.84
    ategorias
    0.80
     plays
    0.78
     study
    0.77
    K
    0.75
    ハ
    0.75
     Both
    0.75
     out
    0.74
     development
    0.74
     both
    0.73
    Activations Density 0.193%

    No Known Activations