© 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. 57606
    Prev
    Next
    INDEX
    Explanations

    elevated, elevation, elevate

    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
     Nevertheless
    -0.97
     Nonetheless
    -0.95
     Likewise
    -0.94
     Occasionally
    -0.91
     المعلومات
    -0.90
     svolge
    -0.89
     tinham
    -0.88
     Utilize
    -0.88
     Commonly
    -0.88
     gleichen
    -0.85
    POSITIVE LOGITS
     elevation
    1.50
     above
    1.48
     Elevation
    1.45
     elevate
    1.41
     Elev
    1.39
     elevar
    1.34
     eleva
    1.30
    Elevated
    1.27
    Elev
    1.27
     elevating
    1.26
    Activations Density 0.014%

    No Known Activations