© 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. 34-GEMMASCOPE-RES-131K
    7. 106787
    Prev
    Next
    INDEX
    Explanations

    washington post

    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
    úcar
    -0.97
     Bloomberg
    -0.94
    Huff
    -0.91
    长江
    -0.91
    Bloomberg
    -0.90
    huff
    -0.87
    bloomberg
    -0.83
     Huffington
    -0.81
    ো
    -0.81
     අ
    -0.80
    POSITIVE LOGITS
    Ars
    0.87
     Scud
    0.83
     Deccan
    0.80
    解釋
    0.79
     Ars
    0.78
     juft
    0.78
     CONCEPT
    0.77
    Existe
    0.77
     amit
    0.75
     FILL
    0.75
    Activations Density 0.082%

    No Known Activations