© 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. 38662
    Prev
    Next
    INDEX
    Explanations

    animated image disposal

    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
    aji
    -0.77
    靖
    -0.75
    Même
    -0.75
     Bar
    -0.74
     airport
    -0.73
    aac
    -0.72
    泄
    -0.72
    ombo
    -0.72
    zono
    -0.72
     zoo
    -0.69
    POSITIVE LOGITS
     dispose
    0.97
     disposal
    0.94
     Disposal
    0.87
    skaya
    0.84
    dispose
    0.83
     delays
    0.82
     Animated
    0.82
    Disposal
    0.82
     animation
    0.81
     GIF
    0.81
    Activations Density 0.020%

    No Known Activations