© 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. 10-GEMMASCOPE-RES-131K
    7. 44360
    Prev
    Next
    INDEX
    Explanations

    Emperor and names or qualifiers

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

    The neuron strongly activates on instances of the title “Emperor.”

    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
    
    -2.73
    ?"
    -2.63
     impec
    -2.47
    ellido
    -2.41
     concernés
    -2.33
    ;"
    -2.33
     '
    -2.28
    小伙伴
    -2.20
     selben
    -2.19
    暾
    -2.19
    POSITIVE LOGITS
    .
    4.09
    <i>
    3.61
    </h1>
    3.50
    </i>
    3.02
    <td>
    2.88
    <b>
    2.70
    t
    2.69
            
    2.63
    ت
    2.58
    The
    2.55
    Activations Density 0.002%

    No Known Activations