© 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. 112500
    Prev
    Next
    INDEX
    Explanations

    actor names

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

    The neuron strongly activates on personal last names (i.e. surnames of people).

    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
    🌝
    -1.36
    🎊
    -1.34
     condicionado
    -1.31
     cansado
    -1.30
    ᓚ
    -1.30
     decidido
    -1.29
    襞
    -1.29
     sketchy
    -1.27
    パンツ
    -1.27
     shady
    -1.27
    POSITIVE LOGITS
    ，
    1.44
    X
    1.43
    tells
    1.38
     largely
    1.36
     Վեր
    1.32
    ︲
    1.30
     sobretudo
    1.30
    acterísticas
    1.28
    ,.
    1.26
     mereka
    1.25
    Activations Density 0.005%

    No Known Activations