© 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. 7991
    Prev
    Next
    INDEX
    Explanations

    question starters

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

    The neuron specializes in spotting question‐related tokens and Q & A language (words like “question,” “questions,” “Q,” “A,” etc.).

    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
    ле
    1.50
    ა
    1.37
    u
    1.29
    м
    1.25
    ص
    1.19
    на
    1.15
    法則
    1.12
    т
    1.10
    к
    1.10
    ಿಕ್
    1.09
    POSITIVE LOGITS
    questions
    1.98
     questions
    1.81
     Questions
    1.81
     otáz
    1.73
     вопросы
    1.68
    QUESTIONS
    1.67
     Fragen
    1.66
     vragen
    1.66
    Questions
    1.66
     QUESTIONS
    1.66
    Activations Density 2.349%

    No Known Activations