© 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. 107974
    Prev
    Next
    INDEX
    Explanations

    millennia and years

    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
     decades
    -0.90
    millions
    -0.86
     millions
    -0.85
     décadas
    -0.79
    Millions
    -0.78
     vittoria
    -0.77
     milyon
    -0.77
    できなかった
    -0.77
     Tuesday
    -0.77
    せずに
    -0.77
    POSITIVE LOGITS
    千年
    1.05
     millennium
    1.01
     mill
    0.90
     centuries
    0.82
    mill
    0.82
     सह
    0.79
    Mill
    0.78
     galle
    0.77
     bim
    0.77
     millennia
    0.75
    Activations Density 0.026%

    No Known Activations