© 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. 1611
    Prev
    Next
    INDEX
    Explanations

    Julian Assange, WikiLeaks

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

    This neuron responds to mentions of high-profile leaks and their sources (e.g. “Julian Assange,” “WikiLeaks,” “U.S. State Department cables”).

    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
     IAS
    -0.78
    縫
    -0.71
    ¯¯
    -0.70
    uertos
    -0.70
    ppell
    -0.69
     NCAA
    -0.69
     ран
    -0.68
    ultura
    -0.68
     inclu
    -0.68
     Fully
    -0.68
    POSITIVE LOGITS
     Wiki
    1.59
    Wiki
    1.47
     Wik
    1.38
    Julian
    1.16
     wik
    1.13
    Wik
    1.13
     Ecuador
    1.13
    Ecuador
    1.10
    Cable
    1.07
     Julian
    1.04
    Activations Density 0.017%

    No Known Activations