© 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. 60488
    Prev
    Next
    INDEX
    Explanations

    a/an followed by a descriptor

    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
     cómics
    -1.01
     there
    -0.98
     dårlig
    -0.95
     spise
    -0.94
     آنجا
    -0.93
    っていきます
    -0.92
     varme
    -0.91
     menganggap
    -0.89
     appuy
    -0.88
    Nadia
    -0.88
    POSITIVE LOGITS
     opportunity
    1.98
     means
    1.82
     glimpse
    1.62
     alternative
    1.59
    means
    1.55
     framework
    1.49
     solution
    1.46
     way
    1.44
     avenue
    1.41
     alternatives
    1.40
    Activations Density 0.072%

    No Known Activations