© 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. 41964
    Prev
    Next
    INDEX
    Explanations

    technical/definitional phrasing

    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
     if
    -2.13
    -
    -1.94
     because
    -1.78
     give
    -1.66
     make
    -1.64
    :
    -1.53
     or
    -1.51
     as
    -1.49
     since
    -1.47
     based
    -1.46
    POSITIVE LOGITS
    嵓
    1.98
     différents
    1.55
     regeringen
    1.55
     necesarios
    1.51
     merav
    1.50
     incrível
    1.49
    臯
    1.49
    
    1.42
     opportunità
    1.42
    logías
    1.42
    Activations Density 0.547%

    No Known Activations