© 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. 73496
    Prev
    Next
    INDEX
    Explanations

    names with nicknames

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

    The neuron detects personal nicknames or aliases enclosed in quotation marks in names (e.g. Javier “Javi” Hernández).

    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
    orak
    -1.67
    !
    -1.42
    .
    -1.37
    簡介
    -1.34
    邹
    -1.31
    トレンド
    -1.31
    慊
    -1.30
    。
    -1.30
     richesse
    -1.29
     varandra
    -1.28
    POSITIVE LOGITS
     memiliki
    1.79
     who
    1.74
     to
    1.67
     akhirnya
    1.56
                        
    1.52
    いいのか
    1.48
     mendapatkan
    1.48
     inapropiados
    1.47
    的人物
    1.46
     also
    1.45
    Activations Density 0.007%

    No Known Activations