© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 70353
    Prev
    Next
    INDEX
    Explanations

    killed many civilians

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

    The neuron is highly sensitive to imperative, scenario-setting cue words—especially “imagine”-style prompts that launch a hypothetical example.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    最后的
    -1.11
    鑲
    -1.06
     나는
    -1.04
     murieron
    -1.03
    étais
    -0.95
    頗
    -0.94
    了嗎
    -0.94
    自然是
    -0.93
    先は
    -0.93
    理由は
    -0.92
    POSITIVE LOGITS
     addirittura
    1.04
    edade
    1.02
     maailman
    1.02
    主人公
    0.96
    文字
    0.96
    tidig
    0.93
    ='';
    0.91
    拳
    0.90
    ycle
    0.90
     tanong
    0.89
    Activations Density 0.087%

    No Known Activations