© 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. 11803
    Prev
    Next
    INDEX
    Explanations

    this followed by a noun or preposition

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

    The neuron is detecting the demonstrative pronoun “this.”

    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
    ης
    1.13
     더욱
    1.03
    ков
    0.98
    ан
    0.97
    Akt
    0.96
    бор
    0.93
    ек
    0.93
    ش
    0.93
     каждом
    0.92
     EnglishChoose
    0.92
    POSITIVE LOGITS
     وهذه
    1.52
     وهذا
    1.23
     particolare
    1.08
    pt
    0.99
     konuda
    0.98
     yüzden
    0.97
    guy
    0.95
     وبه
    0.95
     particular
    0.91
     arada
    0.90
    Activations Density 0.485%

    No Known Activations