© 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. 13440
    Prev
    Next
    INDEX
    Explanations

    calling attention to

    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
    er
    -2.16
     beantworten
    -2.08
     に関する
    -2.05
    鴒
    -1.97
    ’
    -1.97
     だけ
    -1.93
     mencionado
    -1.91
    mpagne
    -1.89
     vermeiden
    -1.87
     as
    -1.80
    POSITIVE LOGITS
    趼
    2.36
    赑
    2.13
    皤
    2.11
    鹮
    2.09
    
    2.02
    菝
    1.96
    絎
    1.95
    銩
    1.94
    踅
    1.90
    檍
    1.89
    Activations Density 0.010%

    No Known Activations