© 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. 81384
    Prev
    Next
    INDEX
    Explanations

    words starting with Ke

    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
     Pretty
    -0.81
     компаний
    -0.80
     Powerful
    -0.80
     wichtigsten
    -0.80
     facet
    -0.79
    蕩
    -0.77
     групп
    -0.75
    帳
    -0.75
     criteria
    -0.73
     Fairly
    -0.73
    POSITIVE LOGITS
     Ke
    1.01
    Ke
    0.97
    Murder
    0.85
     ke
    0.84
    ke
    0.84
    Observe
    0.82
     Observe
    0.79
     ケ
    0.79
    ocrine
    0.78
    сут
    0.76
    Activations Density 0.028%

    No Known Activations