© 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. 34-GEMMASCOPE-RES-131K
    4. 115452
    Prev
    Next
    INDEX
    Explanations

    CPU and GPU usage

    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
     peering
    -0.94
     Added
    -0.91
     шкі
    -0.84
     curtailed
    -0.83
     earphone
    -0.81
     Possibly
    -0.81
     waning
    -0.80
     Lining
    -0.79
     ciertas
    -0.78
     añad
    -0.78
    POSITIVE LOGITS
     utilization
    1.00
    intensive
    0.98
    instruction
    0.95
    ecuted
    0.94
    nite
    0.93
    خوری
    0.92
     prea
    0.88
    wyczaj
    0.87
     folo
    0.87
     afo
    0.87
    Activations Density 0.025%

    No Known Activations