© 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. 10-GEMMASCOPE-RES-131K
    4. 1510
    Prev
    Next
    INDEX
    Explanations

    ambiance, decor, setting, vibe, atmosphere

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

    The neuron fires on words describing a place’s aesthetic atmosphere or decor.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    -2.38
     that
    -1.41
     Either
    -1.31
     $
    -1.30
     самый
    -1.27
    素敵
    -1.26
     Of
    -1.24
    prender
    -1.23
    があるので
    -1.23
     up
    -1.21
    POSITIVE LOGITS
     and
    1.63
    тился
    1.38
     nimmer
    1.34
     verborgen
    1.26
    ėms
    1.23
     bestem
    1.22
     indien
    1.22
    🙊
    1.20
     passend
    1.20
    اسي
    1.19
    Activations Density 0.008%

    No Known Activations