© 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. 37898
    Prev
    Next
    INDEX
    Explanations

    Amnesty International

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

    The neuron is selectively firing on the proper-noun phrase “Amnesty International.”

    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
     IMPRO
    -0.76
    ž
    -0.76
     ও
    -0.76
     mila
    -0.72
    ⠢
    -0.71
    gendes
    -0.70
    menuStrip
    -0.69
     Protocols
    -0.68
    printStats
    -0.68
    Antecedentes
    -0.68
    POSITIVE LOGITS
     AI
    0.92
    止ま
    0.77
    Symbols
    0.77
    稲田
    0.76
    ffen
    0.74
    IAI
    0.73
     coz
    0.72
    writeString
    0.71
    setFill
    0.71
    iscono
    0.70
    Activations Density 0.017%

    No Known Activations