© 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. 116009
    Prev
    Next
    INDEX
    Explanations

    unsigned int types

    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
     destabili
    -0.87
    SizeF
    -0.83
    autonomie
    -0.76
    
    -0.75
    Beaucoup
    -0.75
     lakier
    -0.73
    霖
    -0.72
     groene
    -0.71
    Aujourd
    -0.70
    izop
    -0.70
    POSITIVE LOGITS
     unsigned
    3.14
     uint
    3.13
    uint
    2.80
    unsigned
    2.61
     UInt
    2.06
    Uint
    1.91
    UInt
    1.90
    Unsigned
    1.85
     UINT
    1.82
    UINT
    1.75
    Activations Density 0.102%

    No Known Activations