© 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. 9875
    Prev
    Next
    INDEX
    Explanations

    hotel descriptions and booking

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

    The neuron is selectively activated by the word “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_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
    苼
    -2.09
    क्टर
    -2.05
     implacable
    -2.02
    ꯸
    -2.00
    ötzlich
    -1.97
    砹
    -1.94
     It
    -1.92
     indem
    -1.88
    satunya
    -1.88
    ญี่ป
    -1.88
    POSITIVE LOGITS
    .
    2.81
    ᎒
    2.19
    鉭
    2.09
    _
    2.03
     塗
    2.03
     fabricado
    2.02
    c
    2.02
     it
    2.00
     embarazada
    1.96
    ’?
    1.95
    Activations Density 0.005%

    No Known Activations