© 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. 80794
    Prev
    Next
    INDEX
    Explanations

    cost-effective analysis

    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
     generando
    -0.94
     Fascism
    -0.90
    هل
    -0.89
    
    -0.88
     Salón
    -0.87
     coussin
    -0.87
     moulin
    -0.86
    擁有
    -0.86
     causando
    -0.86
    vendo
    -0.86
    POSITIVE LOGITS
     of
    1.73
     incurred
    1.45
    cost
    1.36
     cost
    1.30
    umer
    1.20
    lier
    1.16
     Cost
    1.13
    liest
    1.12
    ings
    1.06
    liness
    1.06
    Activations Density 0.020%

    No Known Activations