© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40082
    Prev
    Next
    INDEX
    Explanations

    plotting conspiracy scheme

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

    The neuron detects words that refer to secret scheming or conspiratorial plotting.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ↓↓
    -1.87
    －－－－
    -1.81
    ☑️
    -1.78
    🔸
    -1.77
    𝐖
    -1.73
     mohou
    -1.72
    ＂
    -1.71
    ◆◆
    -1.66
    ↑↑
    -1.66
    ↓↓↓
    -1.66
    POSITIVE LOGITS
     not
    2.16
     to
    2.05
     —
    1.88
     A
    1.84
     You
    1.70
    y
    1.70
    —
    1.62
    an
    1.52
     plan
    1.52
     but
    1.51
    Activations Density 0.031%

    No Known Activations