© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14731
    Prev
    Next
    INDEX
    Explanations

    technical identifiers and specifications

    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_22/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
     العربية
    -0.96
    unikasi
    -0.94
    rosoft
    -0.91
     любого
    -0.91
     его
    -0.91
    そのため
    -0.91
     medier
    -0.90
     chiếm
    -0.90
    жела
    -0.90
     }^{
    -0.89
    POSITIVE LOGITS
     both
    1.42
     three
    1.27
    Both
    1.16
     things
    1.12
     different
    1.09
     two
    1.07
     then
    1.02
     sowohl
    0.97
     particolar
    0.94
     thier
    0.94
    Activations Density 0.002%

    No Known Activations