© 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. 72880
    Prev
    Next
    INDEX
    Explanations

    academic and technical abbreviations

    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
    勍
    -3.48
    媗
    -3.47
    
    -3.31
     wodurch
    -3.27
     sodass
    -3.05
     womit
    -3.02
    辚
    -2.98
    汭
    -2.92
    酲
    -2.91
    蒹
    -2.86
    POSITIVE LOGITS
    \
    3.22
    躋
    3.03
    的
    2.84
    是
    2.84
    しばらく
    2.67
    有點
    2.64
     '
    2.64
    ほうが
    2.58
    鉿
    2.55
    頃は
    2.52
    Activations Density 0.057%

    No Known Activations