© 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. 2328
    Prev
    Next
    INDEX
    Explanations

    years 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
     meses
    -1.09
     Krá
    -1.06
     that
    -1.05
     ефек
    -0.96
     condicionado
    -0.95
    metres
    -0.94
    浏
    -0.93
     trouvera
    -0.93
     höl
    -0.93
     semanas
    -0.92
    POSITIVE LOGITS
     سایر
    1.02
     year
    1.00
    饰演
    1.00
    0
    0.96
     года
    0.96
     worin
    0.95
    所说的
    0.94
     yearly
    0.93
    Year
    0.93
    year
    0.92
    Activations Density 0.036%

    No Known Activations