© 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. 48585
    Prev
    Next
    INDEX
    Explanations

    code keywords and syntax

    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
     sobą
    -1.01
    利
    -0.89
    就想
    -0.85
    峨
    -0.82
    了自己
    -0.81
    龈
    -0.80
    來
    -0.80
    訃
    -0.79
     discusión
    -0.78
    ORETICAL
    -0.78
    POSITIVE LOGITS
    ?
    1.02
     {
    1.02
    (){
    1.02
     ווע
    1.02
    ("
    1.00
    {
    0.96
     übernommen
    0.95
    0.94
    (

    0.93
    ?'
    0.93
    Activations Density 0.174%
    No Known Activations