© 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. 10087
    Prev
    Next
    INDEX
    Explanations

    names followed by 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
    憮
    -2.56
    出る
    -2.48
     ヴィンテージ
    -2.48
     Beſ
    -2.42
     misteriosa
    -2.36
     Meningkatkan
    -2.34
     fantástica
    -2.30
     saranno
    -2.30
    は
    -2.30
    м
    -2.28
    POSITIVE LOGITS
          
    2.86
    籥
    2.81
    皝
    2.75
    ꪻ
    2.70
    ar
    2.59
    いいのか
    2.55
    "> 
    2.48
    込め
    2.47
    祤
    2.47
    逦
    2.44
    Activations Density 0.014%

    No Known Activations