© 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. 22-GEMMASCOPE-RES-131K
    7. 15010
    Prev
    Next
    INDEX
    Explanations

    programming variable declarations

    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_22/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
     then
    -1.02
     them
    -1.02
     económica
    -0.89
     económicas
    -0.86
    belum
    -0.85
    pdata
    -0.84
     didn
    -0.83
     loaves
    -0.82
    その後
    -0.81
     wasn
    -0.79
    POSITIVE LOGITS
    ッピング
    1.07
    のだろう
    0.94
    colare
    0.92
    部は
    0.91
     myndig
    0.90
    criminator
    0.88
    :'#
    0.88
    他也
    0.88
    ardez
    0.85
     transitioning
    0.85
    Activations Density 0.006%

    No Known Activations