© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 12598
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on expressions that specify someone’s place of dwelling or location (e.g. “live,” “living,” “in,” “on”).

    oai_token-act-pair · o4-miniTriggered 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
    о
    0.86
    ore
    0.80
    t
    0.77
    ע
    0.76
    ありました
    0.73
    down
    0.71
     -
    0.71
    EY
    0.71
     erhältlich
    0.71
    or
    0.70
    POSITIVE LOGITS
    後に
    0.96
     një
    0.96
     olyan
    0.94
    涯
    0.93
     занима
    0.93
    担心
    0.91
    擔心
    0.90
     μιας
    0.88
    而非
    0.85
    ដែលមាន
    0.84
    Activations Density 0.996%

    No Known Activations