© 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. 60371
    Prev
    Next
    INDEX
    Explanations

    spill containment and settlement

    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
    headless
    -0.76
    atisfaction
    -0.75
    тический
    -0.75
    δ
    -0.72
    勇气
    -0.72
    售后
    -0.71
     Welcome
    -0.71
     кө
    -0.69
    صف
    -0.69
     רו
    -0.68
    POSITIVE LOGITS
     spill
    2.16
     containment
    1.70
     Spill
    1.70
     spills
    1.68
    spill
    1.55
     spilled
    1.53
     Containment
    1.52
    Spill
    1.45
     oil
    1.25
     spilling
    1.12
    Activations Density 0.021%

    No Known Activations