© 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. 48418
    Prev
    Next
    INDEX
    Explanations

    rooted in or grounded in

    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
    imp
    -0.91
    Dam
    -0.88
    shape
    -0.87
     deshalb
    -0.87
    wr
    -0.87
    通し
    -0.86
    ail
    -0.86
     hierbei
    -0.85
    build
    -0.85
    ido
    -0.84
    POSITIVE LOGITS
     in
    2.20
     rooted
    2.06
    rooted
    1.81
     firmly
    1.78
     grounded
    1.66
     roots
    1.45
     Roo
    1.38
    Grounded
    1.32
     root
    1.31
    grounded
    1.31
    Activations Density 0.025%

    No Known Activations