© 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. 86966
    Prev
    Next
    INDEX
    Explanations

    months followed by one

    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
     două
    -0.90
    第二个
    -0.89
     second
    -0.89
     sixteenth
    -0.85
     kedua
    -0.79
     sophomore
    -0.79
     segunda
    -0.79
    兩個
    -0.78
     deuxième
    -0.78
    第二
    -0.77
    POSITIVE LOGITS
     one
    1.82
     ۱
    1.64
     ONE
    1.61
    １
    1.34
     één
    1.34
     satu
    1.34
     واحد
    1.34
     אחד
    1.29
    ۱
    1.26
     One
    1.20
    Activations Density 0.126%

    No Known Activations