© 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. 22-GEMMASCOPE-RES-131K
    7. 33567
    Prev
    Next
    INDEX
    Explanations

    revenge and vengeance

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

    The main thing this neuron does is find words related to revenge or retribution.

    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
    P
    -1.92
    当時は
    -1.91
    N
    -1.72
     roligt
    -1.67
     層
    -1.65
    thschild
    -1.58
    很難
    -1.58
    鎂
    -1.56
     helg
    -1.54
     updated
    -1.52
    POSITIVE LOGITS
    ↵
    1.88
    CHREIB
    1.79
    COLOG
    1.70
    СКИ
    1.63
    栊
    1.63
    岽
    1.62
    那些
    1.54
     vengeance
    1.54
    ти
    1.53
     niya
    1.50
    Activations Density 0.012%

    No Known Activations