© 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. 119595
    Prev
    Next
    INDEX
    Explanations

    collect the terms

    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
    ↵↵
    -4.03
    ed
    -3.53
    e
    -3.28
            
    -3.27
    il
    -3.16
    The
    -3.14
    v
    -3.13
     -
    -3.11
    f
    -3.09
    V
    -3.09
    POSITIVE LOGITS
    𞤤
    3.59
    垕
    3.50
    偸
    3.48
    Ꮵ
    3.30
    
    3.16
     书法
    3.06
    
    3.06
    ciutto
    3.02
    ୌ
    2.98
    𞤪
    2.94
    Activations Density 0.011%

    No Known Activations