© 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. 84821
    Prev
    Next
    INDEX
    Explanations

    tab menu bar background

    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
    زاری
    -0.81
     dichter
    -0.79
    emias
    -0.78
    modb
    -0.77
    lapsible
    -0.76
    wla
    -0.76
    と言い
    -0.76
     bedenken
    -0.76
    iego
    -0.75
    Thoughts
    -0.75
    POSITIVE LOGITS
     background
    2.22
    background
    1.88
     Background
    1.63
    Background
    1.63
    背景
    1.55
     shadow
    1.46
     backgrounds
    1.46
     Hintergrund
    1.40
     backdrop
    1.40
    bg
    1.37
    Activations Density 0.041%

    No Known Activations