© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63559
    Prev
    Next
    INDEX
    Explanations

    turn of the century

    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
     early
    -1.35
     mid
    -1.12
     late
    -1.07
     دهه
    -0.92
     year
    -0.90
     end
    -0.87
     década
    -0.85
     đầu
    -0.85
     beginning
    -0.84
     later
    -0.81
    POSITIVE LOGITS
     ۱۱
    0.95
     PREVIOUS
    0.93
    Previous
    0.90
     ۰
    0.90
     Previous
    0.88
     прошлого
    0.87
    previous
    0.87
     vorige
    0.82
     previous
    0.81
    zinho
    0.81
    Activations Density 0.031%

    No Known Activations