© 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. 15121
    Prev
    Next
    INDEX
    Explanations

    names of famous people

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

    The main thing this neuron does is detect and activate on personal proper names (i.e., individual people’s 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_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
     sua
    -1.31
    ,.
    -1.31
     also
    -1.29
     others
    -1.28
    —
    -1.26
    gués
    -1.26
    s
    -1.23
     wyja
    -1.19
     especific
    -1.19
     in
    -1.19
    POSITIVE LOGITS
     nadru
    1.31
     patienter
    1.22
     samti
    1.20
     män
    1.20
     etui
    1.20
     marta
    1.19
     erin
    1.18
     énergé
    1.16
     >",
    1.16
     magasiner
    1.15
    Activations Density 0.052%

    No Known Activations