© 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. 7911
    Prev
    Next
    INDEX
    Explanations

    people and their descriptions

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

    The neuron strongly activates on occurrences of the word “people.”

    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
    ুদ্ধ
    1.30
    ل
    1.22
     nghiệm
    1.20
     mực
    1.16
    はこちら
    1.14
    larından
    1.13
     inputted
    1.12
     мате
    1.09
     xác
    1.08
    кої
    1.04
    POSITIVE LOGITS
    ד
    1.52
    ли
    1.48
    ا
    1.23
    tr
    1.23
    मय
    1.20
    تر
    1.19
    friendly
    1.19
     publiques
    1.19
    ം
    1.16
    ten
    1.15
    Activations Density 0.025%

    No Known Activations