© 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. 84600
    Prev
    Next
    INDEX
    Explanations

    code structure and symbols

    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
    
    -0.88
     saudara
    -0.87
    似乎
    -0.85
    任何
    -0.85
     barata
    -0.84
     aidé
    -0.83
     ADDRESS
    -0.83
    corrhi
    -0.82
     Länge
    -0.82
    লা
    -0.82
    POSITIVE LOGITS
     public
    1.30
    public
    1.20
     reise
    1.07
     constant
    1.01
     private
    1.00
     lyd
    0.98
    private
    0.97
     mahu
    0.95
     takk
    0.95
     rask
    0.94
    Activations Density 0.002%

    No Known Activations