© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 6953
    Prev
    Next
    INDEX
    Explanations

    two-dimensional

    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
    interopRequire
    -0.76
    <0xA1>
    -0.76
    4
    -0.76
     친
    -0.73
    meris
    -0.72
     dynamical
    -0.71
     raken
    -0.70
    jang
    -0.70
     세
    -0.70
     Miser
    -0.69
    POSITIVE LOGITS
    二维
    3.11
     planar
    2.19
    平面
    1.90
     plane
    1.78
     дву
    1.64
     flat
    1.55
     two
    1.54
    planar
    1.50
    Two
    1.49
     плоско
    1.48
    Activations Density 0.118%

    No Known Activations