© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8598
    Prev
    Next
    INDEX
    Explanations

    structured data delimiters

    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
    _
    -1.42
    0
    -1.40
    ;
    -1.37
    .
    -1.35
     only
    -1.34
     oldu
    -1.33
    私たちは
    -1.33
    erobic
    -1.32
    mentação
    -1.32
    我們
    -1.31
    POSITIVE LOGITS
     protože
    1.51
     particularmente
    1.46
     attraverso
    1.46
    莇
    1.44
     entweder
    1.40
     particolarmente
    1.38
    ejercicio
    1.38
     gotta
    1.38
     ヴィンテージ
    1.34
    
    1.34
    Activations Density 0.005%

    No Known Activations