© 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. 92250
    Prev
    Next
    INDEX
    Explanations

    cos words or roots

    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
     Muck
    -0.81
    ﾁ
    -0.78
    斂
    -0.77
    かというと
    -0.76
     専用
    -0.76
     Dolls
    -0.75
     ("\
    -0.75
     bỏ
    -0.75
     完成
    -0.74
     Fabrics
    -0.74
    POSITIVE LOGITS
     cos
    1.90
     Cos
    1.79
    cos
    1.59
     COS
    1.54
    Cos
    1.42
     cosy
    1.19
     Cosmo
    1.16
     Kos
    1.15
    COS
    1.14
     kos
    1.12
    Activations Density 0.015%

    No Known Activations