© 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. 10-GEMMASCOPE-RES-131K
    7. 339
    Prev
    Next
    INDEX
    Explanations

    dialogs, alerts, and views

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     jelasnya
    -1.14
     eerst
    -1.13
     パス
    -1.13
    τική
    -1.12
     admitted
    -1.08
     .(
    -1.07
     étaient
    -1.06
     テ
    -1.06
     提示
    -1.06
    between
    -1.05
    POSITIVE LOGITS
    でいい
    1.09
    Одна
    1.07
    关于
    1.07
     my
    1.06
    ophageal
    1.04
    >//
    1.02
    牛肉
    1.00
     gynnwys
    1.00
     मुझे
    0.99
    getServer
    0.99
    Activations Density 0.057%

    No Known Activations