© 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. 34-GEMMASCOPE-RES-131K
    7. 31896
    Prev
    Next
    INDEX
    Explanations

    Iran nuclear deal

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

    The neuron strongly activates on mentions of nuclear or atomic‐energy topics and related institutions.

    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
     woman
    -0.79
    djang
    -0.79
     injury
    -0.74
    是一个
    -0.73
     Belinda
    -0.72
    麓
    -0.71
     gerçekleşti
    -0.69
    🥟
    -0.69
    出発
    -0.68
     hidden
    -0.68
    POSITIVE LOGITS
     Iran
    1.66
     JC
    1.44
     nuclear
    1.40
     Iranian
    1.33
     Nuclear
    1.29
    Nuclear
    1.27
    Iran
    1.26
     NUCLEAR
    1.16
     iran
    1.16
    nuclear
    1.16
    Activations Density 0.013%

    No Known Activations