© 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. 10-GEMMASCOPE-RES-131K
    7. 112442
    Prev
    Next
    INDEX
    Explanations

    legal rights and concepts

    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
     as
    -1.88
     with
    -1.84
     would
    -1.66
     mainly
    -1.52
     having
    -1.52
     widely
    -1.51
     mostly
    -1.50
     rique
    -1.48
     بسیار
    -1.48
     good
    -1.45
    POSITIVE LOGITS
     the
    1.94
     insanely
    1.42
     unbelievably
    1.41
    every
    1.38
     masterful
    1.38
     astonishing
    1.36
     dando
    1.34
    Ð
    1.34
    !!!!!!!!!
    1.34
     первой
    1.33
    Activations Density 0.105%

    No Known Activations