© 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. 7870
    Prev
    Next
    INDEX
    Explanations

    cancellation via forms or direct methods

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

    This neuron fires on the short caption‐ or sidebar‐style metadata lines (e.g. photo captions, calls to action, “follow us,” “join the discussion,” image credits) rather than the main article 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
     for
    0.98
     для
    0.88
    針對
    0.84
    ForSettings
    0.83
     барои
    0.83
     untuk
    0.82
     برای
    0.81
     براي
    0.81
     permettant
    0.78
     helfen
    0.77
    POSITIVE LOGITS
    នៅលើ
    1.03
    ในสนาม
    0.97
    ຢູ່ໃນ
    0.96
    อยู่ใน
    0.95
    บน
    0.94
    ใน
    0.92
     kwenye
    0.92
    自己在
    0.91
     në
    0.91
     ở
    0.90
    Activations Density 1.654%

    No Known Activations