© 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. 22-GEMMASCOPE-RES-131K
    4. 67311
    Prev
    Next
    INDEX
    Explanations

    future continuation

    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
     fauteuil
    -1.01
    ђу
    -0.96
     huile
    -0.96
     нажмите
    -0.94
     symbole
    -0.92
     famí
    -0.92
     directrice
    -0.91
     bantu
    -0.91
     bross
    -0.91
     traktor
    -0.90
    POSITIVE LOGITS
     future
    2.02
     was
    1.55
     przysz
    1.41
     künftig
    1.41
    今後
    1.38
    future
    1.34
    以后
    1.27
     experience
    1.25
    今後も
    1.22
     next
    1.15
    Activations Density 0.061%

    No Known Activations