© 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. 82557
    Prev
    Next
    INDEX
    Explanations

    it seems

    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
     dezen
    -0.75
    ruff
    -0.75
     yksi
    -0.75
    λοι
    -0.74
    ۫
    -0.73
     ミニ
    -0.72
    航天
    -0.70
    ígen
    -0.70
    タコ
    -0.70
    vant
    -0.69
    POSITIVE LOGITS
     seems
    3.27
     seem
    2.78
     Seems
    2.72
    Seems
    2.50
    seems
    2.30
     scheint
    1.98
     кажется
    1.98
     parece
    1.82
     seemed
    1.81
    seem
    1.62
    Activations Density 0.044%

    No Known Activations