© 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. 39647
    Prev
    Next
    INDEX
    Explanations

    coordinates enclosed in parentheses

    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
     contextLoads
    -0.90
    显著
    -0.81
     to
    -0.81
     repur
    -0.78
     ‘‘
    -0.77
     теперь
    -0.77
     usual
    -0.77
     事
    -0.76
    Descricao
    -0.75
    山市
    -0.75
    POSITIVE LOGITS
     there
    0.97
     it
    0.95
     FEES
    0.89
     atento
    0.85
    Pipes
    0.84
     SUPPLY
    0.82
     snows
    0.82
     bekämp
    0.81
    kamers
    0.81
    itinéraire
    0.81
    Activations Density 0.004%

    No Known Activations