© 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. 45498
    Prev
    Next
    INDEX
    Explanations

    times and dates

    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
    ämän
    -0.89
     predisposition
    -0.85
    陸軍
    -0.79
    град
    -0.79
    baga
    -0.79
     reproduce
    -0.77
     that
    -0.77
    客様
    -0.76
     почти
    -0.74
    ][:
    -0.74
    POSITIVE LOGITS
     evening
    1.38
     noon
    1.35
     afternoon
    1.21
     Saturday
    1.19
    Saturday
    1.08
    evening
    1.00
     sunset
    0.91
     sundown
    0.90
     cuatro
    0.90
    絶対に
    0.89
    Activations Density 0.015%

    No Known Activations