© 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. 22-GEMMASCOPE-RES-131K
    7. 14301
    Prev
    Next
    INDEX
    Explanations

    dates and times

    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
     negatif
    -0.89
    zeichnis
    -0.88
     sayang
    -0.87
    اہ
    -0.85
     chré
    -0.85
     Anno
    -0.85
     rokok
    -0.82
     telur
    -0.82
     btc
    -0.80
    邀
    -0.80
    POSITIVE LOGITS
     immediately
    1.08
    แค่
    0.98
     subsequent
    0.96
     teorías
    0.94
    new
    0.89
     overnight
    0.89
     instantly
    0.89
     emergency
    0.88
     news
    0.88
     Emergency
    0.86
    Activations Density 0.001%

    No Known Activations