© 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. 7133
    Prev
    Next
    INDEX
    Explanations

    get started or get it

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

    The neuron primarily detects occurrences of the word “get.”

    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
    你
    1.31
    是我
    1.28
     dotyczą
    1.24
     jantar
    1.24
    ları
    1.19
     giờ
    1.19
    異なる
    1.19
    یت
    1.18
    まだ
    1.17
    の子
    1.17
    POSITIVE LOGITS
     rid
    1.79
    rän
    1.44
    у
    1.41
    о
    1.27
     antérieure
    1.16
    id
    1.12
    iatric
    1.10
    ยิน
    1.08
     phép
    1.07
    AsyncKeyState
    1.07
    Activations Density 0.273%

    No Known Activations