© 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. 84697
    Prev
    Next
    INDEX
    Explanations

    having a hard time

    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
     nagu
    -0.81
     alkohol
    -0.78
     scotch
    -0.77
    marginVertical
    -0.76
     '=',
    -0.75
    ybė
    -0.74
    henti
    -0.73
    ⁝
    -0.72
    fromDate
    -0.72
     gitar
    -0.71
    POSITIVE LOGITS
     time
    5.25
    time
    2.64
     times
    2.41
     время
    2.08
    Time
    2.06
     czasu
    1.90
     времени
    1.90
     tijd
    1.87
     समय
    1.87
     Time
    1.82
    Activations Density 0.009%

    No Known Activations