© 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. 22-GEMMASCOPE-RES-131K
    7. 130891
    Prev
    Next
    INDEX
    Explanations

    relationship between elements

    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_22/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
     dobry
    -1.07
     polski
    -0.87
     eaten
    -0.85
    引っ
    -0.84
     that
    -0.82
    ukt
    -0.81
    equalTo
    -0.80
    Ȋ
    -0.79
    﨑
    -0.79
     есть
    -0.79
    POSITIVE LOGITS
     keduanya
    1.11
     latter
    1.09
     häm
    0.89
     lät
    0.88
     kär
    0.88
     män
    0.83
     maksi
    0.82
     tän
    0.81
    Repos
    0.81
    Both
    0.79
    Activations Density 0.130%

    No Known Activations