© 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. 85307
    Prev
    Next
    INDEX
    Explanations

    worth mentioning or taking

    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
    _
    -2.20
    {
    -2.11
    ti
    -1.91
    to
    -1.85
     The
    -1.84
     mehrfach
    -1.78
    =
    -1.75
    在大
    -1.73
    with
    -1.73
    ii
    -1.73
    POSITIVE LOGITS
    却被
    1.79
    ٶ
    1.74
    ܃
    1.70
    变了
    1.66
    鮡
    1.66
    却是
    1.66
    囖
    1.62
    ,  
    1.61
    グルト
    1.60
    吀
    1.60
    Activations Density 0.004%

    No Known Activations