© 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. 5488
    Prev
    Next
    INDEX
    Explanations

    What comes next in questions

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

    This neuron specifically detects occurrences of the question word “What.”

    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
    ی
    1.58
     tạp
    1.19
    る
    1.15
    гти
    1.11
    ை
    1.10
    എ
    1.10
    י
    1.08
    ます
    1.07
    eeee
    1.06
    ee
    1.05
    POSITIVE LOGITS
     касается
    1.02
    in
    0.96
    on
    0.94
    types
    0.91
     وما
    0.90
    ✔️
    0.82
    ~~
    0.81
    impress
    0.81
     linhas
    0.80
     endereco
    0.80
    Activations Density 0.064%

    No Known Activations