© 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. 128302
    Prev
    Next
    INDEX
    Explanations

    The neuron selectively activates on capitalized personal names—especially last names of authors, contributors, or notable individuals.

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

    Names from people

    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
    !
    -2.03
    :
    -2.02
    \
    -1.96
    _
    -1.79
    ;
    -1.77
    ,
    -1.70
    zdroj
    -1.62
    差異
    -1.54
     nine
    -1.52
     viable
    -1.52
    POSITIVE LOGITS
    ckeye
    2.31
    ificantly
    2.25
    琑
    2.22
    ledad
    2.19
    fordshire
    2.13
    ——”
    2.11
    romeda
    2.09
    rsquo
    2.09
    StoryboardSegue
    2.08
    olge
    2.06
    Activations Density 0.075%

    No Known Activations