© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117789
    Prev
    Next
    INDEX
    Explanations

    writing and communication

    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
     also
    -0.88
    美しい
    -0.86
     apapun
    -0.85
    чительно
    -0.84
    instagram
    -0.82
    auso
    -0.81
    istical
    -0.80
     quedó
    -0.79
     then
    -0.79
     cuando
    -0.77
    POSITIVE LOGITS
     writing
    1.42
     пишу
    1.27
     write
    1.19
    writing
    1.17
     письмо
    1.12
    message
    1.05
     writes
    1.05
     emailing
    1.04
     contacting
    1.04
     reaching
    1.04
    Activations Density 0.073%

    No Known Activations