© 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. 98753
    Prev
    Next
    INDEX
    Explanations

    criminal complaints and investigations

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

    The main thing this neuron does is detect words and phrases related to legal actions and court proceedings.

    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
     Trieb
    -0.80
    וה
    -0.77
    centa
    -0.75
    -',
    -0.75
    VIRGO
    -0.73
     vineyards
    -0.71
    Endereço
    -0.71
    hermosa
    -0.71
    髋
    -0.70
    adita
    -0.69
    POSITIVE LOGITS
     criminal
    5.69
    criminal
    4.31
    Criminal
    4.06
     Criminal
    3.86
     CRIMINAL
    3.53
     crimin
    3.33
     уголов
    3.17
    刑事
    2.56
    CRIM
    2.45
     criminality
    2.45
    Activations Density 0.101%

    No Known Activations