© 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. 15486
    Prev
    Next
    INDEX
    Explanations

    academic or technical terms

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

    The neuron strongly activates on mentions of company or brand names (proper nouns identifying service providers).

    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
    .
    0.69
    /
    0.67
    <eos>
    0.66
    ͡
    0.63
    ZZ
    0.62
    +
    0.62
    THE
    0.61
    _
    0.61
    ্য
    0.61
    et
    0.59
    POSITIVE LOGITS
    idega
    0.71
     پروژه
    0.70
    櫳
    0.67
    फेक्ट
    0.66
    स्टेंस
    0.66
     fasteners
    0.66
     Бек
    0.65
     कंप्लीट
    0.64
    लीट
    0.64
    abhavo
    0.64
    Activations Density 0.015%

    No Known Activations