© 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. 8347
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on words naming removal or destruction processes (e.g. surgical excisions, cell lysis, deletions).

    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
    คุณ
    0.81
    𝕀
    0.70
     हमको
    0.70
    巅峰
    0.67
    𝕆
    0.64
    こちらの
    0.63
    在他
    0.62
    Џ
    0.61
    𝕖
    0.61
     acredito
    0.61
    POSITIVE LOGITS
    removal
    0.89
     detoxification
    0.85
     lysis
    0.83
     removal
    0.83
    smittel
    0.82
     of
    0.81
     odstr
    0.80
     τῶν
    0.80
     удалить
    0.79
     удаления
    0.78
    Activations Density 0.000%

    No Known Activations