© 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. 34-GEMMASCOPE-RES-131K
    4. 110933
    Prev
    Next
    INDEX
    Explanations

    facilities and amenities

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

    The neuron spots mentions of leisure or facility amenities (e.g. spa, theater, pool, hotel).

    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
     of
    -1.40
     from
    -1.36
     through
    -1.26
     their
    -1.24
     the
    -1.19
     encontraban
    -1.14
     then
    -1.09
     arasındaki
    -1.09
     different
    -1.05
     Umgebung
    -1.04
    POSITIVE LOGITS
     with
    1.71
     for
    1.55
     where
    1.38
     departement
    1.34
    สำหรับ
    1.28
     جهت
    1.25
     volant
    1.23
     для
    1.19
     available
    1.16
     casco
    1.16
    Activations Density 0.054%

    No Known Activations