© 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. 34-GEMMASCOPE-RES-131K
    7. 33426
    Prev
    Next
    INDEX
    Explanations

    nestled, situated, surrounded

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

    The neuron picks out commercial real-estate or lodging/venue marketing language—terms advertising spaces to rent or buy.

    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
     هنگام
    -0.88
     selaku
    -0.82
    adak
    -0.80
    鏖
    -0.79
     couverte
    -0.78
     decken
    -0.77
    juta
    -0.76
    رائ
    -0.75
     warszaw
    -0.75
     üzerinden
    -0.75
    POSITIVE LOGITS
     surrounded
    4.34
     amid
    2.73
     amidst
    2.48
     rodeado
    2.23
     surround
    2.17
     Amid
    2.14
    Amid
    2.08
    amid
    2.05
     entour
    1.97
     midst
    1.94
    Activations Density 0.064%

    No Known Activations