© 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. 4766
    Prev
    Next
    INDEX
    Explanations

    digging a hole

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

    The neuron spotlights multi‐token stretches of song or poem lyrics (i.e. continuous quoted or verse‐style lines).

    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
    该
    0.76
    具有
    0.76
    यदि
    0.76
     kişinin
    0.74
     अन्य
    0.71
     hitherto
    0.71
     nedenle
    0.68
     extensive
    0.66
    本文
    0.65
    व्यक्ति
    0.65
    POSITIVE LOGITS
     Gonna
    0.95
     nigga
    0.93
     gonna
    0.87
     sueños
    0.80
     bisschen
    0.79
    してる
    0.74
     любви
    0.74
     gegangen
    0.74
     ねえ
    0.73
     yeah
    0.73
    Activations Density 0.023%

    No Known Activations