© 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. 45618
    Prev
    Next
    INDEX
    Explanations

    sql query results

    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
    жнарод
    -0.94
     odkry
    -0.94
     */;
    -0.93
    haden
    -0.89
    WebpackPlugin
    -0.88
    Ɵ
    -0.88
    
    -0.88
     carattere
    -0.88
     Desenvolvimento
    -0.88
    ---|---|
    -0.87
    POSITIVE LOGITS
     chilena
    1.01
    尔的
    0.97
    য়া
    0.88
    @
    0.78
     varandra
    0.78
     rather
    0.78
     มาก
    0.78
     проф
    0.77
     británica
    0.76
    Autre
    0.74
    Activations Density 0.013%

    No Known Activations