© 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. 25986
    Prev
    Next
    INDEX
    Explanations

    weightedsum knapsack profit

    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
    ế
    -0.74
    WriteAttribute
    -0.72
    bouw
    -0.72
    bios
    -0.71
     Sitz
    -0.71
    glBegin
    -0.70
    天皇
    -0.70
    ichy
    -0.69
    八
    -0.69
     весной
    -0.68
    POSITIVE LOGITS
     kna
    1.45
    kna
    1.36
     weight
    1.32
    Kna
    1.23
     profit
    1.23
     WEIGHT
    1.22
    psack
    1.20
     weights
    1.20
     knap
    1.19
    WEIGHT
    1.15
    Activations Density 0.009%

    No Known Activations