© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1329
    Prev
    Next
    INDEX
    Explanations

    re- prefix for sharing, repeating, or technical terms

    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
    resistance
    -0.76
    reducer
    -0.71
    ραγ
    -0.68
     Recreational
    -0.68
    Rounded
    -0.67
     Representative
    -0.67
     Refund
    -0.66
     Renew
    -0.66
    erdo
    -0.66
     rencontrer
    -0.66
    POSITIVE LOGITS
     re
    4.06
     repost
    2.84
     ре
    2.36
    Repost
    2.34
     Re
    2.20
    Re
    1.94
    re
    1.88
     إعادة
    1.88
    再
    1.83
    重新
    1.69
    Activations Density 0.066%

    No Known Activations