© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6274
    Prev
    Next
    INDEX
    Explanations

    HOME commands and features

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

    The neuron fires on mentions of concrete named entities or resource/object types (e.g. “matter,” “export,” “Container,” “Direct Messaging,” “experiences,” 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
    ني
    0.78
    低于
    0.68
    angleOf
    0.66
    某种
    0.63
     gewisse
    0.62
    肝
    0.62
    喎
    0.62
    矢
    0.62
    氐
    0.61
    睥
    0.60
    POSITIVE LOGITS
     oluştur
    0.89
     içeren
    0.76
     personnaliser
    0.73
     dakika
    0.73
     creation
    0.71
     Tết
    0.71
     kullanarak
    0.71
     만들기
    0.71
    er
    0.70
     ద్వారా
    0.70
    Activations Density 0.164%

    No Known Activations