© 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. 14038
    Prev
    Next
    INDEX
    Explanations

    related to other people or things

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

    The neuron detects reciprocal relationship phrases, especially “each other” or “one another.”

    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
    ﺎ
    1.16
    ED
    1.15
    ET
    1.14
    TS
    1.13
    DA
    1.09
    ad
    1.03
    ่ะ
    1.02
    RIC
    1.01
    TE
    1.00
    TA
    0.99
    POSITIVE LOGITS
    fected
    0.80
     تواند
    0.77
    洺
    0.73
     peers
    0.72
     constantly
    0.72
     peoples
    0.70
     마찬가지
    0.70
     Евро
    0.70
    总之
    0.70
     Planets
    0.68
    Activations Density 0.078%

    No Known Activations