© 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. 59307
    Prev
    Next
    INDEX
    Explanations

    names followed by surnames

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

    This neuron activates on tokens that look like named entities or technical labels—proper names, acronyms, or measurement symbols.

    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
    
    -2.55
    欤
    -2.53
     lofty
    -2.52
    </sup>
    -2.50
    をはじめ
    -2.48
     persino
    -2.47
     zajíma
    -2.47
    indows
    -2.44
    uminazione
    -2.41
    kemeja
    -2.39
    POSITIVE LOGITS
    er
    3.20
    J
    3.09
    1
    3.09
    G
    3.02
    s
    3.00
    (
    2.94
    .
    2.81
    ar
    2.81
    This
    2.80
    On
    2.70
    Activations Density 0.012%

    No Known Activations