© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 98530
    Prev
    Next
    INDEX
    Explanations

    local places

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

    The neuron fires strongly on prepositional location phrases that use possessive pronouns—especially “your” or “their”—as in “at your local …” or “from their local ….”

    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
    autre
    -0.94
     autre
    -0.93
    owała
    -0.86
    verlauf
    -0.83
    อื่น
    -0.82
    alité
    -0.79
     revista
    -0.79
    isée
    -0.78
    far
    -0.77
     другая
    -0.77
    POSITIVE LOGITS
     local
    3.48
    local
    2.33
     nearest
    2.25
     nearby
    2.20
     мест
    2.06
     your
    2.05
    当地
    1.95
     neighborhood
    1.93
     місце
    1.88
     lokalen
    1.80
    Activations Density 0.066%

    No Known Activations