© 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. 8043
    Prev
    Next
    INDEX
    Explanations

    why it's

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

    The neuron detects heading-style questions or benefit intros in job-ad or promotional text (e.g. “Here’s what’s in it for you:” or “What you will get…”).

    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
    蠵
    0.72
     무료
    0.68
     அனைத்து
    0.66
     ڈالر
    0.66
     PHONE
    0.64
     gesturing
    0.64
    問い合わせ
    0.63
    poetrycommunity
    0.63
     pleural
    0.63
     teléfonos
    0.63
    POSITIVE LOGITS
     things
    0.90
    you
    0.79
    :
    0.77
     you
    0.75
    Things
    0.75
    Benefits
    0.73
     we
    0.72
    Characteristics
    0.71
    你的
    0.70
    你
    0.70
    Activations Density 0.017%

    No Known Activations