© 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. 13573
    Prev
    Next
    INDEX
    Explanations

    what happened to

    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
     cinquième
    -1.81
     mismos
    -1.66
     cortesía
    -1.59
    illante
    -1.54
     quatrième
    -1.52
     mantiene
    -1.49
     verschillende
    -1.48
     mesmos
    -1.48
     если
    -1.47
    if
    -1.46
    POSITIVE LOGITS
     would
    1.52
     on
    1.52
     for
    1.52
    ,
    1.45
     more
    1.33
     about
    1.31
     like
    1.30
     with
    1.28
    ง่าย
    1.27
     en
    1.25
    Activations Density 0.038%

    No Known Activations