© 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. 34-GEMMASCOPE-RES-131K
    7. 78253
    Prev
    Next
    INDEX
    Explanations

    police chief commissioner officer

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

    The main thing this neuron does is detect mentions of “police chief” (i.e. references to police leadership).

    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
     department
    -1.05
     soldiers
    -0.97
     Department
    -0.96
     departments
    -0.92
     court
    -0.86
     offices
    -0.81
     criminal
    -0.81
     government
    -0.79
     army
    -0.79
     office
    -0.78
    POSITIVE LOGITS
     مدير
    0.84
     adhé
    0.84
    GARY
    0.80
    =$("#
    0.79
    ार्थ
    0.77
     DIRECTOR
    0.77
    _->
    0.77
     contribué
    0.76
    richText
    0.76
    σι
    0.75
    Activations Density 0.038%

    No Known Activations