© 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. 22-GEMMASCOPE-RES-131K
    4. 71470
    Prev
    Next
    INDEX
    Explanations

    locations after prepositions

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

    The neuron strongly activates on the preposition “in,” especially when it introduces locations or temporal phrases.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     sitios
    -1.31
    逦
    -1.25
     hábit
    -1.24
    ,.
    -1.22
     offre
    -1.19
     và
    -1.16
     restaurant
    -1.16
     project
    -1.16
    骉
    -1.16
    alties
    -1.14
    POSITIVE LOGITS
     egenskaper
    1.07
    Kamer
    1.03
    Francia
    1.03
    няют
    1.02
     With
    1.02
     ефек
    1.02
    معرفی
    0.98
     From
    0.98
    Mening
    0.97
     after
    0.97
    Activations Density 0.066%

    No Known Activations