© 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. 65462
    Prev
    Next
    INDEX
    Explanations

    electrical power and charging

    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
     пен
    -0.90
     retirement
    -0.90
     retired
    -0.88
     retire
    -0.88
    Retirement
    -0.79
    retirement
    -0.77
     Retired
    -0.77
     fantasy
    -0.74
     dru
    -0.72
    Retired
    -0.71
    POSITIVE LOGITS
     banks
    1.18
     bank
    1.18
     power
    1.16
     portable
    1.15
    Backup
    1.13
     mAh
    1.13
    BANK
    1.10
     solar
    1.09
     emergency
    1.08
    solar
    1.06
    Activations Density 0.007%

    No Known Activations