© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60769
    Prev
    Next
    INDEX
    Explanations

    name Cruz or place Santa Cruz

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

    The neuron fires on every occurrence of the token “Cruz,” i.e. proper‐name uses of “Cruz” in people’s names or place 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_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
    珑
    -2.59
     oppressive
    -2.47
    ى
    -2.45
    蹰
    -2.42
    袪
    -2.31
    ჱ
    -2.28
     hinder
    -2.27
     pragmatic
    -2.22
    あります
    -2.20
    tituto
    -2.19
    POSITIVE LOGITS
    k
    2.95
    鐃
    2.45
    羕
    2.42
    我要
    2.36
    焿
    2.28
    緇
    2.22
    $
    2.09
     felpa
    2.05
     "";
    2.03
    搋
    2.03
    Activations Density 0.005%

    No Known Activations