© 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. 34-GEMMASCOPE-RES-131K
    7. 48393
    Prev
    Next
    INDEX
    Explanations

    accused or charged with crimes

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

    The neuron strongly activates on words naming professions, official roles, or legal institutions (e.g. psychiatrist, Representative, President, Court, man).

    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
     Carsten
    -0.78
    ↥
    -0.76
     éte
    -0.74
    に触
    -0.74
    受害
    -0.72
     élev
    -0.71
     rightful
    -0.71
    itulo
    -0.70
     着物
    -0.70
    本当は
    -0.69
    POSITIVE LOGITS
     accused
    5.31
     charged
    3.58
    accu
    3.20
     suspected
    2.88
    charged
    2.66
     обви
    2.64
     acusado
    2.59
     accuse
    2.55
     Charged
    2.41
     accus
    2.30
    Activations Density 0.076%

    No Known Activations