© 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. 12414
    Prev
    Next
    INDEX
    Explanations

    timed sequences and delays

    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
    allero
    -0.90
     предме
    -0.90
    EXHIB
    -0.89
    Remarque
    -0.89
     投
    -0.89
     ücret
    -0.87
    了出去
    -0.85
    contenedor
    -0.83
    Forza
    -0.82
    épreuve
    -0.82
    POSITIVE LOGITS
     delays
    1.11
     szabály
    1.02
     wait
    1.02
     delayed
    0.94
     móds
    0.94
     delay
    0.93
     timed
    0.93
    จัง
    0.92
     waiting
    0.92
     timings
    0.91
    Activations Density 0.197%

    No Known Activations