© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 70178
    Prev
    Next
    INDEX
    Explanations

    names ending in iz, kat, an, he, adin, el, ad, rk, diff, oki

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

    The neuron detects multi‐token capitalized proper names (especially fictional character 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_34/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
     it
    -0.85
     helps
    -0.84
    キャラ
    -0.81
    追記
    -0.79
     this
    -0.78
    もとも
    -0.78
    録画
    -0.77
     美しい
    -0.77
    最高的
    -0.77
    It
    -0.77
    POSITIVE LOGITS
     Pharmaceuticals
    0.98
     INDUSTRIES
    0.96
    DataSnapshot
    0.95
     AspNetCore
    0.95
     CITY
    0.94
    pected
    0.94
     Coil
    0.93
    agrad
    0.92
    grad
    0.91
     الفي
    0.91
    Activations Density 0.033%

    No Known Activations