© 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. 38983
    Prev
    Next
    INDEX
    Explanations

    class and built-in operations

    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
     sempre
    -2.03
    ścioła
    -1.73
    начально
    -1.69
    媗
    -1.66
    ̚
    -1.66
    eynman
    -1.63
    鸲
    -1.59
    gebras
    -1.59
     サムネイル
    -1.59
    ꦢ
    -1.58
    POSITIVE LOGITS
     großem
    1.87
    {
    1.84
    0
    1.77
     him
    1.75
     Your
    1.67
    뿅
    1.65
    .
    1.64
     Why
    1.63
     this
    1.60
     hohem
    1.60
    Activations Density 0.011%

    No Known Activations