© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106408
    Prev
    Next
    INDEX
    Explanations

    Location, Location, Location

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

    The neuron is keyed to the word “location” (or “Location”) when it appears as a field or heading label.

    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
    摇了摇头
    -1.14
     risultato
    -1.10
    
    -1.06
    
    -1.04
    mbgg
    -1.04
     mutil
    -1.04
     scrivere
    -1.03
     fraî
    -1.03
    𐌺
    -1.03
    envoyer
    -1.02
    POSITIVE LOGITS
    📍
    1.23
    alised
    1.20
    RelativeTo
    1.13
     nových
    1.04
     buzzing
    1.02
    .
    1.02
     where
    0.99
     specific
    0.98
    oku
    0.98
     premiere
    0.98
    Activations Density 0.030%

    No Known Activations