© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 59804
    Prev
    Next
    INDEX
    Explanations

    years and quantities

    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
     ten
    -1.76
     Ten
    -1.67
     zehn
    -1.65
    Ten
    -1.56
     Eleven
    -1.34
     twelve
    -1.31
     десять
    -1.31
    twelve
    -1.29
     TEN
    -1.28
     tenth
    -1.28
    POSITIVE LOGITS
     fifty
    3.33
    Fifty
    3.08
     Fifty
    2.91
     forty
    2.86
     sixty
    2.83
    fifty
    2.72
    Sixty
    2.50
     Sixty
    2.44
     seventy
    2.42
    Forty
    2.39
    Activations Density 0.123%

    No Known Activations