© 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. 60325
    Prev
    Next
    INDEX
    Explanations

    recent years or months

    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
    prz
    -0.98
    tyk
    -0.91
     Meille
    -0.90
    āti
    -0.88
    ఞ
    -0.86
    cipital
    -0.84
     disiplin
    -0.82
    Reminders
    -0.81
     lender
    -0.81
    Hid
    -0.80
    POSITIVE LOGITS
     years
    3.97
     months
    2.61
     weeks
    2.23
    years
    2.23
     days
    1.98
     times
    1.94
     year
    1.68
     años
    1.65
    Years
    1.63
     decades
    1.60
    Activations Density 0.027%

    No Known Activations