© 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. 10-GEMMASCOPE-RES-131K
    7. 23923
    Prev
    Next
    INDEX
    Explanations

    and the

    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_10/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
     článku
    -1.73
     Pokud
    -1.72
    értelmű
    -1.69
    ју
    -1.66
    ggling
    -1.65
    觑
    -1.64
     móds
    -1.60
     válto
    -1.59
    
    -1.56
     uppgifter
    -1.55
    POSITIVE LOGITS
     the
    2.44
     then
    1.95
    ↵
    1.92
     it
    1.79
     this
    1.75
    {
    1.63
    </i>
    1.43
    ]
    1.43
    ment
    1.43
     + 
    1.41
    Activations Density 0.022%

    No Known Activations