© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 70480
    Prev
    Next
    INDEX
    Explanations

    code syntax

    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_22/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
     esclavos
    -0.99
    bende
    -0.98
    ſo
    -0.93
     gancho
    -0.93
     consumidor
    -0.92
    ikä
    -0.91
     картинка
    -0.90
    אם
    -0.88
    studied
    -0.88
    。  
    -0.88
    POSITIVE LOGITS
     their
    1.10
     these
    1.02
     better
    1.00
     سبب
    0.97
     those
    0.93
     much
    0.88
    /***
    
    0.80
     concentrating
    0.78
     försö
    0.78
    cl
    0.77
    Activations Density 0.002%

    No Known Activations