© 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-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 4603
    Prev
    Next
    INDEX
    Explanations

    around

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

    The neuron strongly fires on instances of the word “around” when it appears in the phrase “around the world.”

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

    the phrase "around the world" or similar geographic scope expressions.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    phrases indicating worldwide scope, especially constructions like “around the world” or “around the globe.”

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ן
    0.98
    рия
    0.94
     হ্যাঁ
    0.93
     или
    0.92
    নি
    0.91
     wären
    0.90
     wäre
    0.89
     volna
    0.88
     cré
    0.88
    ский
    0.88
    POSITIVE LOGITS
    s
    1.55
    e
    1.30
    tc
    1.26
    tint
    1.25
    a
    1.25
    tors
    1.23
    tables
    1.21
    aft
    1.20
    tone
    1.19
    atts
    1.16
    Activations Density 0.012%

    No Known Activations