© 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. 4358
    Prev
    Next
    INDEX
    Explanations

    PostgreSQL SQL queries

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

    The neuron fires most strongly on proper names and named entities (people, places, organizations).

    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
    IList
    0.53
    IoT
    0.48
    🖼
    0.47
    🌡
    0.47
    🍱
    0.46
    LOGGER
    0.45
    আরো
    0.45
    🚛
    0.44
    なぁ
    0.43
    🥣
    0.43
    POSITIVE LOGITS
     convictions
    0.55
     frontman
    0.54
     assailant
    0.54
    il
    0.53
     semifinal
    0.53
     Securities
    0.50
     denials
    0.50
     estadounidense
    0.49
     prosecutions
    0.49
     Corp
    0.49
    Activations Density 2.020%

    No Known Activations