© 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. 34-GEMMASCOPE-RES-131K
    4. 80780
    Prev
    Next
    INDEX
    Explanations

    configuration and gem files

    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
     cocción
    -0.81
     Parkplatz
    -0.77
     preguntar
    -0.77
     estreno
    -0.77
    mujeres
    -0.76
     összefoglaló
    -0.76
    
    -0.75
    
    -0.75
    貴族
    -0.75
     العنوان
    -0.72
    POSITIVE LOGITS
    config
    1.08
     config
    1.01
     cfg
    0.96
     configure
    0.92
    cfg
    0.87
    利亚
    0.84
    exception
    0.81
     configur
    0.79
    gat
    0.77
     Theil
    0.77
    Activations Density 0.045%

    No Known Activations