© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74287
    Prev
    Next
    INDEX
    Explanations

    code and data structures

    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
    b
    -1.82
     if
    -1.73
    c
    -1.70
    z
    -1.65
     of
    -1.63
    Critic
    -1.50
    那时候
    -1.48
    n
    -1.48
    f
    -1.46
    INTRODUCCIÓN
    -1.45
    POSITIVE LOGITS
     \&
    1.48
     fantástica
    1.45
     auténtica
    1.45
     defekt
    1.45
     maravillosa
    1.45
    aş
    1.41
    
    1.38
    \'{
    1.37
     живут
    1.36
     pantalones
    1.34
    Activations Density 0.553%

    No Known Activations