© 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. 128300
    Prev
    Next
    INDEX
    Explanations

    names and regions

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

    This neuron fires on personal surnames (capitalized last names) in citations or references.

    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
    琁
    -3.08
    橚
    -3.00
    䛗
    -2.97
     teclas
    -2.88
     aguj
    -2.86
     tomba
    -2.86
    鸶
    -2.83
     artesan
    -2.78
     espé
    -2.77
    Ⲉ
    -2.75
    POSITIVE LOGITS
    ↵
    4.97
    </b>
    3.73
    m
    3.63
    o
    3.42
    in
    3.34
    mu
    3.28
    ar
    3.27
    sh
    3.02
    )$
    3.02
    </i>
    2.98
    Activations Density 0.005%

    No Known Activations