© 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. 34-GEMMASCOPE-RES-131K
    7. 59872
    Prev
    Next
    INDEX
    Explanations

    recent past experiences

    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
     constant
    -1.04
     tomorrow
    -1.04
     första
    -1.02
     kog
    -1.01
     still
    -0.99
     geko
    -0.98
     nästa
    -0.98
    [++
    -0.97
    +
    -0.96
     Mangel
    -0.96
    POSITIVE LOGITS
     lately
    2.55
    Recently
    2.33
     recently
    2.23
    recently
    2.13
     recientemente
    1.77
     myself
    1.67
     Recently
    1.66
     både
    1.66
     since
    1.65
    recent
    1.63
    Activations Density 0.094%

    No Known Activations