© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 8183
    Prev
    Next
    INDEX
    Explanations

    automóvil or automobiles

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

    This neuron identifies words and phrases used in giving advice or instructions (e.g., guideline language).

    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
     刺繍
    0.85
     근데
    0.84
     underpinned
    0.80
     tbh
    0.79
     ร่วม
    0.79
    💔
    0.78
     Embroidery
    0.77
    🪐
    0.75
     可愛い
    0.75
    cambrian
    0.73
    POSITIVE LOGITS
     noted
    0.86
     persons
    0.82
     automobile
    0.78
     automóvil
    0.77
     odors
    0.77
     telephone
    0.77
     favorite
    0.76
     automobiles
    0.76
     करीत
    0.75
     motorist
    0.73
    Activations Density 0.249%

    No Known Activations