© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 45295
    Prev
    Next
    INDEX
    Explanations

    death records

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

    The neuron fires on tokens associated with license, copyright, and legal‐header boilerplate (e.g. “//”, “Copyright”, “License”, “Supreme Court”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    爱情
    -0.89
     România
    -0.85
    |'.'
    -0.84
    靭
    -0.84
     purplish
    -0.83
     Taus
    -0.83
    店铺
    -0.82
     acoso
    -0.81
     Fonction
    -0.80
    caption
    -0.79
    POSITIVE LOGITS
     death
    1.11
     Death
    0.96
     deaths
    0.92
    死亡
    0.89
     mort
    0.86
    Deaths
    0.85
    Death
    0.85
     сегодня
    0.85
     DEATH
    0.84
    DEATH
    0.82
    Activations Density 0.001%

    No Known Activations