© 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. 103066
    Prev
    Next
    INDEX
    Explanations

    UI list item handling

    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
     mandatory
    -0.82
     newly
    -0.82
     verdict
    -0.81
     estimates
    -0.79
     kvar
    -0.79
     required
    -0.78
     quickly
    -0.77
     leveraging
    -0.77
     neatly
    -0.77
     executive
    -0.77
    POSITIVE LOGITS
    EventHandler
    1.11
     refle
    0.88
    ){//
    0.85
     EventHandler
    0.83
    shall
    0.82
     SHALL
    0.81
    indicated
    0.81
     искрен
    0.80
     Contoh
    0.80
    among
    0.80
    Activations Density 0.000%

    No Known Activations