© 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. 10394
    Prev
    Next
    INDEX
    Explanations

    Included with AWS accounts

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

    The neuron isn’t picking out any specific words or concepts—instead its activation steadily climbs with how deep into the text you are, effectively marking “later” tokens.

    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
    फिल्म
    0.63
    Этот
    0.62
    center
    0.62
    それぞれの
    0.61
    Sebelum
    0.60
     एकेडमी
    0.59
    Dengan
    0.59
    攙
    0.59
     专业
    0.58
    艿
    0.58
    POSITIVE LOGITS
     Liaison
    0.68
     obten
    0.63
     Conven
    0.63
     permitirá
    0.62
     Collect
    0.60
    .--
    0.59
     criança
    0.58
     Representations
    0.57
     Advertising
    0.57
     Obligations
    0.57
    Activations Density 0.000%

    No Known Activations