© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20112
    Prev
    Next
    INDEX
    Explanations

    locations followed by regions

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

    The neuron fires on standalone numeric tokens—especially decimal or integer values—such as measurements, coordinates, or other numbers in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    locative phrases that specify proximity or position relative to named places (e.g., “near/in/outside” followed by geographic place names).

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    locations near cities or towns, typically indicated by the preposition "near" followed by a place name.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     paff
    -1.23
     tomat
    -1.22
     recientemente
    -1.21
    ﹶ
    -1.19
     consumi
    -1.19
     買
    -1.16
     pering
    -1.16
     utilisé
    -1.16
    
    -1.16
    闆
    -1.13
    POSITIVE LOGITS
     about
    1.27
     to
    1.22
     seul
    1.17
    x
    1.09
        
    1.09
    }\
    1.07
    About
    1.07
     около
    1.05
    ются
    1.05
     on
    1.05
    Activations Density 0.068%

    No Known Activations