© 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. 31-GEMMASCOPE-2-RES-16K
    7. 10548
    Prev
    Next
    INDEX
    Explanations

    would be

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

    The neuron fires strongly on occurrences of the base-form verb “be.”

    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_31_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
    હિ
    0.61
    Domains
    0.55
    シ
    0.55
    Hier
    0.54
    اه
    0.54
    마
    0.53
     Truck
    0.52
    齋
    0.52
    회의
    0.52
    Truck
    0.52
    POSITIVE LOGITS
     doing
    0.59
     homework
    0.59
     वालों
    0.58
     observant
    0.56
     laugh
    0.55
     మనం
    0.54
     आवेग
    0.54
    ibald
    0.54
     optional
    0.53
     ලබා
    0.53
    Activations Density 0.000%

    No Known Activations