© 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. 22-GEMMASCOPE-RES-131K
    7. 70788
    Prev
    Next
    INDEX
    Explanations

    timing and delayed execution

    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
     distinguer
    -1.11
     célè
    -1.01
     alcune
    -1.00
    بدون
    -0.98
     hinzugefügt
    -0.97
     différentes
    -0.96
     успех
    -0.96
    ראות
    -0.95
    帔
    -0.94
    の歴史
    -0.94
    POSITIVE LOGITS
     time
    1.23
     epitom
    1.06
     after
    1.01
    $
    0.96
     or
    0.96
    Ḥ
    0.94
     ingrained
    0.94
     delayed
    0.93
     postpon
    0.93
     delay
    0.91
    Activations Density 0.007%

    No Known Activations