© 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. 4842
    Prev
    Next
    INDEX
    Explanations

    coins, events, alarms, gastritis, physics

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

    This neuron responds to two-word noun–noun compound phrases (e.g. “subject matter,” “brick pavers”).

    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
     a
    0.91
    字符
    0.76
    労働
    0.75
    branchNode
    0.75
     folhas
    0.75
    뺄
    0.75
    移除
    0.74
     their
    0.72
    ӕ
    0.71
     Änderung
    0.71
    POSITIVE LOGITS
     concierge
    0.75
     असल्याने
    0.71
    ակի
    0.71
    ased
    0.70
     comprising
    0.69
    സമ
    0.69
     comprise
    0.68
     Since
    0.68
    inating
    0.68
     Considering
    0.67
    Activations Density 0.000%

    No Known Activations