© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101235
    Prev
    Next
    INDEX
    Explanations

    crimes against humanity and war crimes

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

    This neuron detects mentions of serious crimes and related legal institutions (e.g., war crimes, crimes against humanity, tribunals, and international criminal justice).

    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
    乄
    -1.55
     asegurarse
    -1.45
     Réponses
    -1.45
     französische
    -1.41
     plafon
    -1.41
    ANIEL
    -1.41
    骉
    -1.40
     comunicarse
    -1.39
     antidesliz
    -1.38
    nouvelle
    -1.38
    POSITIVE LOGITS
    0
    1.48
    𝚕
    1.41
    </strong>
    1.38
     >&
    1.36
     geringen
    1.25
     it
    1.24
    żdż
    1.17
    anément
    1.16
    kreis
    1.15
    들에게
    1.15
    Activations Density 0.009%

    No Known Activations