© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67614
    Prev
    Next
    INDEX
    Explanations

    significant quantity or degree

    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
     parem
    -1.44
    翆
    -1.34
     terça
    -1.33
     nepri
    -1.32
     hein
    -1.31
     huk
    -1.31
     traktor
    -1.30
    萏
    -1.30
     automobili
    -1.30
     اطلع
    -1.30
    POSITIVE LOGITS
    ↵↵
    1.82
     different
    1.56
    𝜙
    1.48
     zrobić
    1.48
     
    1.43
     encuentras
    1.41
    l
    1.38
    關鍵
    1.25
     Different
    1.24
    关键
    1.24
    Activations Density 0.105%

    No Known Activations