© 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. 93026
    Prev
    Next
    INDEX
    Explanations

    hotels and event venues

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

    The neuron fires on explicit place or venue mentions—i.e. location names (often hotels or event sites) together with their “at”/“in” prepositions.

    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
    octanol
    -0.79
    Hardware
    -0.77
    тится
    -0.74
     منزل
    -0.71
    oog
    -0.71
     similares
    -0.70
     apartamento
    -0.68
     Requis
    -0.68
    OFFICE
    -0.66
    쫓
    -0.66
    POSITIVE LOGITS
     convention
    1.36
     ballroom
    1.16
     conference
    1.16
     hotel
    1.11
     Convention
    1.09
    会议
    1.02
     conventions
    1.00
     resort
    1.00
    Convention
    0.98
     Conventions
    0.95
    Activations Density 0.021%

    No Known Activations