© 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. 34-GEMMASCOPE-RES-131K
    7. 58611
    Prev
    Next
    INDEX
    Explanations

    UI background properties

    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_34/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
    NSP
    -0.90
    making
    -0.86
     zufrieden
    -0.82
    arashtra
    -0.81
    屉
    -0.79
    ouwen
    -0.78
    textView
    -0.78
    Decline
    -0.77
    UILabel
    -0.76
    ぶり
    -0.75
    POSITIVE LOGITS
    background
    2.36
     background
    2.28
     Background
    2.08
    Background
    1.87
    BACKGROUND
    1.84
     backgrounds
    1.64
     bg
    1.55
     Hintergrund
    1.49
    背景
    1.48
     背景
    1.48
    Activations Density 0.016%

    No Known Activations