© 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. 90972
    Prev
    Next
    INDEX
    Explanations

    statistical analysis and methodology

    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
    cheidung
    -0.94
     praktis
    -0.90
    tratamiento
    -0.89
     teolog
    -0.89
     caballeros
    -0.89
     anden
    -0.88
     disiplin
    -0.88
     sensores
    -0.88
    يده
    -0.87
     controladores
    -0.87
    POSITIVE LOGITS
     exposures
    0.94
     ineligible
    0.92
     strata
    0.91
     estimates
    0.91
     бампер
    0.91
     epidemio
    0.91
     blinded
    0.90
    bastien
    0.86
     stratified
    0.85
     mmol
    0.85
    Activations Density 0.425%

    No Known Activations