© 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. 1244
    Prev
    Next
    INDEX
    Explanations

    Allan and MacDonald names

    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
    0
    -2.81
    However
    -2.50
    และ
    -2.45
    鑿
    -2.39
     "..\..\
    -2.39
    ing
    -2.31
    But
    -2.25
    颀
    -2.22
     ця
    -2.19
    ة
    -2.13
    POSITIVE LOGITS
    ⟝
    3.08
    鹇
    2.73
    
    2.72
    就去
    2.66
    鹮
    2.50
    蒾
    2.48
    潆
    2.48
    戋
    2.42
    罽
    2.38
    ᚺ
    2.36
    Activations Density 0.002%

    No Known Activations