© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85562
    Prev
    Next
    INDEX
    Explanations

    words starting with Ro

    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_10/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
    踽
    -3.50
    茕
    -3.22
    蚍
    -3.17
    慙
    -3.17
    圌
    -3.08
    秾
    -3.03
    縂
    -3.00
    麈
    -2.95
     hinh
    -2.91
    茈
    -2.86
    POSITIVE LOGITS
     be
    3.06
    0
    3.03
     Lately
    2.94
     Now
    2.91
     was
    2.91
     Personally
    2.89
    2
    2.83
     Currently
    2.81
     Maintaining
    2.80
    In
    2.77
    Activations Density 0.004%

    No Known Activations