© 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. 76531
    Prev
    Next
    INDEX
    Explanations

    words starting with Ker

    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
     delicado
    -0.75
     fewer
    -0.74
     less
    -0.73
     lengan
    -0.73
     violations
    -0.73
     delicada
    -0.72
     Intent
    -0.72
     intentions
    -0.71
     repaired
    -0.71
     rewrite
    -0.70
    POSITIVE LOGITS
     Кер
    1.10
     Ker
    1.07
    Ker
    1.00
    ker
    0.93
     ker
    0.93
     KER
    0.87
    mit
    0.83
    FOOT
    0.83
    cher
    0.81
    ċ
    0.79
    Activations Density 0.018%

    No Known Activations