© 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. 45540
    Prev
    Next
    INDEX
    Explanations

    positive descriptive adjectives

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

    The neuron fires on terms describing lodging experiences and amenities (e.g. “home,” “stay,” “room,” “clean,” “kitchen,” etc.) in vacation-rental or hotel reviews.

    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
     geschreven
    -0.94
    ładka
    -0.93
     אַ
    -0.91
    iranje
    -0.89
    ELESS
    -0.88
     متعلقه
    -0.87
    κρα
    -0.87
    abinieri
    -0.87
    лябин
    -0.86
    ⏤
    -0.86
    POSITIVE LOGITS
     spacious
    2.11
     modern
    2.00
     clean
    1.98
     comfortable
    1.76
    modern
    1.55
     tidy
    1.53
     well
    1.48
     equipped
    1.47
     modem
    1.38
    Modern
    1.35
    Activations Density 0.046%

    No Known Activations