© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9423
    Prev
    Next
    INDEX
    Explanations

    The main thing this neuron does is detect words and phrases that indicate purchasing actions (e.g., buy, buying, bought, order).

    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
     patios
    0.55
     treasures
    0.53
     walkways
    0.53
    巅
    0.52
     temptations
    0.52
     nays
    0.51
     flyers
    0.50
     έχουν
    0.49
     knobs
    0.49
     dealerships
    0.48
    POSITIVE LOGITS
    this
    0.64
    <0x80>
    0.63
    и
    0.61
    о
    0.55
    and
    0.53
    го
    0.52
    у
    0.52
     this
    0.50
    а
    0.50
     Args
    0.49
    Activations Density 0.003%

    No Known Activations