© 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. 42599
    Prev
    Next
    INDEX
    Explanations

    mathematical multiplication symbols

    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
     probablemente
    -1.80
    на
    -1.72
    )
    -1.54
    -1.51
                 
    -1.46
    
    -1.44
     todavía
    -1.41
     to
    -1.41
                               
    -1.37
                     
    -1.36
    POSITIVE LOGITS
     the
    1.74
     umożli
    1.63
     tesettür
    1.61
     muun
    1.57
    ίων
    1.52
    瘪
    1.52
     maquilla
    1.51
    獁
    1.50
     priser
    1.48
     sacré
    1.47
    Activations Density 0.009%

    No Known Activations