© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 60833
    Prev
    Next
    INDEX
    Explanations

    license file

    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
     if
    -1.42
     puisqu
    -0.93
     since
    -0.91
     although
    -0.88
     HUB
    -0.88
    زيل
    -0.88
     agr
    -0.87
     until
    -0.86
     messi
    -0.85
     unless
    -0.84
    POSITIVE LOGITS
     then
    2.44
     thì
    1.82
     entonces
    1.77
    then
    1.58
     Then
    1.55
    的话
    1.54
     dann
    1.52
    的話
    1.50
     allora
    1.45
     alors
    1.37
    Activations Density 0.069%

    No Known Activations