© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 65511
    Prev
    Next
    INDEX
    Explanations

    programming and legal directives

    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
    𓆜
    -3.02
    𞤤
    -2.64
    ðsíða
    -2.58
    𓆟
    -2.45
    acterísticas
    -2.41
    嫱
    -2.39
    琹
    -2.38
     gänzlich
    -2.38
    ("");
    
    -2.34
     allzu
    -2.33
    POSITIVE LOGITS
    箆
    3.14
    ൎ
    3.06
     ajouter
    2.78
    铙
    2.67
     возможности
    2.64
    ܜ
    2.58
    辚
    2.52
    mathrm
    2.47
    переди
    2.39
    迓
    2.39
    Activations Density 0.003%

    No Known Activations