© 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. 34-GEMMASCOPE-RES-131K
    4. 73628
    Prev
    Next
    INDEX
    Explanations

    background images or content

    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
    orari
    -0.77
    jungan
    -0.75
    buttonText
    -0.73
    pinMode
    -0.72
     Scul
    -0.71
    Chiara
    -0.71
     sculptures
    -0.71
    delle
    -0.71
    GLUT
    -0.70
     chisel
    -0.69
    POSITIVE LOGITS
     background
    3.97
    background
    3.14
     backgrounds
    3.09
     Background
    3.03
    Background
    2.95
    背景
    2.83
    BACKGROUND
    2.50
    BackgroundImage
    2.42
     BACKGROUND
    2.38
     backdrop
    2.34
    Activations Density 0.048%

    No Known Activations