© 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. 22-GEMMASCOPE-RES-131K
    7. 129089
    Prev
    Next
    INDEX
    Explanations

    This neuron activates on proper names—particularly character and person names—in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    names and family members

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     einfach
    -1.04
     especially
    -0.95
     이름
    -0.89
     ersten
    -0.87
     azonban
    -0.85
    Sic
    -0.84
     Gläub
    -0.84
     interacción
    -0.82
    饑
    -0.82
    Katso
    -0.82
    POSITIVE LOGITS
     voz
    1.05
    ₚ
    1.02
     занимается
    0.99
     يقوم
    0.99
     arrive
    0.95
    thead
    0.94
    ออกมา
    0.94
     thoſe
    0.93
     incoming
    0.93
    phony
    0.93
    Activations Density 0.008%

    No Known Activations