© 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. 97869
    Prev
    Next
    INDEX
    Explanations

    recalling past experiences and memories

    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
     last
    -1.75
     yesterday
    -1.73
    去年
    -1.63
     છે
    -1.45
    目前
    -1.43
     kemarin
    -1.39
     afgelopen
    -1.38
     bisher
    -1.34
     gestern
    -1.34
     Yesterday
    -1.32
    POSITIVE LOGITS
     later
    1.87
     my
    1.83
     back
    1.78
     remembers
    1.74
     those
    1.73
    当時の
    1.61
    那时候
    1.59
    当時は
    1.56
    Later
    1.56
     memories
    1.55
    Activations Density 0.038%

    No Known Activations