© 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. 22-GEMMASCOPE-RES-131K
    7. 67913
    Prev
    Next
    INDEX
    Explanations

    Alfons Heck

    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_22/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
     Projektu
    -1.25
    Ɍ
    -1.02
     nuevamente
    -1.02
    âni
    -0.99
    ясь
    -0.99
    Šalt
    -0.99
     necesit
    -0.98
    年来
    -0.96
    ┈
    -0.96
     Į
    -0.93
    POSITIVE LOGITS
     unless
    1.16
     as
    1.09
     初始化
    1.08
     too
    1.07
     либо
    0.93
     potřeb
    0.93
    cisive
    0.93
     launch
    0.91
     until
    0.90
    ȃ
    0.90
    Activations Density 0.009%

    No Known Activations