© 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. 108957
    Prev
    Next
    INDEX
    Explanations

    on

    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
     löyty
    -1.53
     liitty
    -1.43
     tehdä
    -1.30
     käyttää
    -1.28
     tarjo
    -1.22
     pitä
    -1.22
     olivat
    -1.21
    ]){
    -1.21
     actionPerformed
    -1.20
     restent
    -1.19
    POSITIVE LOGITS
     on
    8.06
     On
    2.63
    บน
    2.38
     على
    2.34
     на
    2.31
    on
    2.31
     trên
    2.06
    On
    1.90
     ON
    1.85
     på
    1.83
    Activations Density 0.038%

    No Known Activations