© 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. 35779
    Prev
    Next
    INDEX
    Explanations

    residential amenities

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

    The neuron detects mentions of real‐estate amenities and communal facilities (e.g. clubhouse, pools, gym, HOA activities).

    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
     Cantidad
    -1.20
     Bemerkungen
    -1.20
    niña
    -1.16
    ῖς
    -1.14
     that
    -1.13
    X
    -1.11
    ovina
    -1.10
     sufre
    -1.09
     lutego
    -1.08
     Ergän
    -1.07
    POSITIVE LOGITS
     pelu
    1.18
     bacté
    1.16
     parcours
    1.13
     zodia
    1.13
     courrier
    1.09
     caricatura
    1.09
     Sú
    1.09
     operar
    1.09
     linge
    1.08
     légumes
    1.06
    Activations Density 0.006%

    No Known Activations