© 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. 86555
    Prev
    Next
    INDEX
    Explanations

    Kenney, Quake, Kanye

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

    The neuron fires on specific entity or terminology tokens—proper names (e.g. Quake, Kenney, Trent) and specialized technical nouns (e.g. hydration, nave).

    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
     noteworthy
    -2.66
    两年
    -2.50
     незавер
    -2.42
     averiguar
    -2.34
     getEmail
    -2.27
    fır
    -2.27
    王的
    -2.22
    
    -2.22
     areas
    -2.19
    л
    -2.19
    POSITIVE LOGITS
    i
    4.03
    ي
    3.27
    1
    3.09
    寕
    3.03
     anún
    2.92
    い
    2.91
    厛
    2.88
    𖣘
    2.86
    s
    2.83
    י
    2.81
    Activations Density 0.006%

    No Known Activations