© 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. 10-GEMMASCOPE-RES-131K
    7. 105410
    Prev
    Next
    INDEX
    Explanations

    bribe, bribes, bribery

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

    The main thing this neuron does is detect mentions of bribery or corruption payments (e.g., “bribe,” “bribing,” “bribes,” “kickbacks”).

    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
    (
    -3.05
    c
    -3.00
    p
    -2.84
    d
    -2.80
    n
    -2.78
    f
    -2.75
    <em>
    -2.67
    is
    -2.55
    ch
    -2.48
    ']
    -2.45
    POSITIVE LOGITS
     花纹
    2.34
    潆
    2.23
    歘
    2.20
    鉏
    2.16
    籥
    2.13
     dijeron
    2.09
    颏
    2.09
    お勧め
    2.06
    pág
    2.05
    щество
    2.03
    Activations Density 0.004%

    No Known Activations