© 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. 504
    Prev
    Next
    INDEX
    Explanations

    Processing graphics and coding

    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
     depressions
    -0.88
     Ciné
    -0.88
     pecan
    -0.86
     トゥ
    -0.82
     Plano
    -0.80
    éez
    -0.77
     Tourisme
    -0.77
     Wok
    -0.75
    ランチ
    -0.75
     onyx
    -0.75
    POSITIVE LOGITS
     sketch
    1.15
     mouseClicked
    1.08
     Processing
    1.01
    ellipse
    0.99
     mouseY
    0.97
    println
    0.96
    sketch
    0.92
    mouseX
    0.90
    strokeWeight
    0.90
    createCanvas
    0.90
    Activations Density 0.013%

    No Known Activations