© 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. 104380
    Prev
    Next
    INDEX
    Explanations

    other, others, each other and related foreign terms

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

    The neuron detects words and phrases that express conversion, equivalence, or measurement (e.g. “equivalent,” “into,” “same,” “measure,” “amount”).

    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
     for
    -0.90
     even
    -0.82
    izielle
    -0.82
    起伏
    -0.81
    ії
    -0.80
     Notebook
    -0.79
    пой
    -0.78
    дол
    -0.78
    生日
    -0.74
    neuri
    -0.74
    POSITIVE LOGITS
     others
    1.67
     each
    1.64
     eachother
    1.52
    others
    1.41
     other
    1.41
    Others
    1.36
    彼此
    1.31
     друг
    1.28
     opposite
    1.23
     anderen
    1.21
    Activations Density 0.087%

    No Known Activations