© 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. 10470
    Prev
    Next
    INDEX
    Explanations

    Murdoch Smith Rupert Graves

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

    This neuron responds to mentions of Rupert Murdoch (and closely associated named entities like his companies or related inquiry names).

    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
    
    -2.84
     ferrovia
    -2.38
     tomba
    -2.16
     princesse
    -2.14
     imagined
    -2.06
    嶇
    -2.02
    觧
    -2.02
    。
    -2.02
     jupe
    -1.98
    This
    -1.97
    POSITIVE LOGITS
    ↵
    2.95
    <i>
    2.83
    .
    2.53
    </b>
    2.38
     tomando
    2.22
     beinahe
    2.14
    2.11
     The
    2.09
    </i>
    2.03
    ised
    2.02
    Activations Density 0.003%

    No Known Activations