© 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. 129828
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    $
    -1.06
     by
    -1.04
     with
    -1.02
    并
    -0.96
    目前
    -0.94
     TMPro
    -0.91
     only
    -0.89
    並
    -0.89
     pungkasnya
    -0.89
    ੧
    -0.89
    POSITIVE LOGITS
     vermutlich
    1.13
     hauptsächlich
    1.09
     keineswegs
    1.08
     meistens
    1.03
    ční
    1.01
    حدى
    1.00
     keines
    0.98
     ode
    0.98
     hierbei
    0.96
    <0xD6>
    0.94
    Activations Density 0.000%

    No Known Activations