© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47991
    Prev
    Next
    INDEX
    Explanations

    vacations and holidays

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

    The neuron detects words and phrases related to traveling or being away on vacation.

    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
     Obst
    -0.84
    ⛸
    -0.80
     reaſon
    -0.80
    лоси
    -0.79
    หมือน
    -0.78
    endix
    -0.77
    })-\
    -0.77
    ͦ
    -0.74
     elektrische
    -0.73
    ænd
    -0.72
    POSITIVE LOGITS
     vacation
    6.16
     vacations
    4.66
     holiday
    4.25
     Vacation
    4.25
    vacation
    4.22
    Vacation
    4.09
     holidays
    3.81
     vacaciones
    3.38
     Urlaub
    3.36
    holiday
    3.16
    Activations Density 0.107%

    No Known Activations