© 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. 119755
    Prev
    Next
    INDEX
    Explanations

    all modifying phrase

    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
    ’
    -2.64
     in
    -1.78
     ‘
    -1.76
     belangrijk
    -1.52
     jedną
    -1.51
    蔼
    -1.45
     ’
    -1.43
     off
    -1.43
     try
    -1.40
     wenigen
    -1.38
    POSITIVE LOGITS
    ®.
    1.73
     stör
    1.70
     なお
    1.65
    
    1.63
    hålla
    1.63
    irmanship
    1.55
    メ
    1.52
    ﹔
    1.51
    åter
    1.48
     これ
    1.47
    Activations Density 0.016%

    No Known Activations