© 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. 90796
    Prev
    Next
    INDEX
    Explanations

    code assignments and declarations

    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
     $=-
    -0.96
    =−
    -0.78
     className
    -0.77
    คือ
    -0.75
    cog
    -0.75
    🪶
    -0.71
     parecido
    -0.71
     $=\
    -0.71
    illen
    -0.70
    ServiceImpl
    -0.69
    POSITIVE LOGITS
    "]
    
    0.98
    })
    
    0.85
    '))
    
    0.82
    several
    0.82
    "))
    
    0.82
     LATER
    0.81
    Several
    0.80
    Mab
    0.80
    ())
    
    0.79
    YOUR
    0.79
    Activations Density 0.094%

    No Known Activations