© 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. 349
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on direct second-person address—especially on “you” and “your” (and related reader-directed phrasing) in instructional or promotional text.

    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
    iswa
    0.42
     este
    0.40
    or
    0.39
    elen
    0.39
    勉
    0.39
     වලින්
    0.38
    ia
    0.38
     abil
    0.38
    heden
    0.38
     meget
    0.38
    POSITIVE LOGITS
     Ảnh
    0.50
    ("./
    0.49
    (/*
    0.49
     Bugün
    0.47
    账
    0.45
    (([
    0.45
     Kiến
    0.45
     Eindruck
    0.45
    漣
    0.45
    ('',
    0.44
    Activations Density 0.000%

    No Known Activations