© 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. 8280
    Prev
    Next
    INDEX
    Explanations

    steps or process descriptions

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

    The neuron is specialized to detect occurrences of the word “process.”

    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
    n
    1.96
    न
    1.48
    ن
    1.47
    am
    1.44
    ot
    1.44
    un
    1.41
    on
    1.38
    ri
    1.38
    to
    1.38
    is
    1.33
    POSITIVE LOGITS
     Processes
    1.87
    Processes
    1.64
     Proces
    1.63
    過程
    1.59
     Proses
    1.59
    밟
    1.59
    过程
    1.58
     processes
    1.56
    流程
    1.56
    يان
    1.55
    Activations Density 0.040%

    No Known Activations