© 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. 129474
    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
     this
    -1.31
     during
    -1.17
     even
    -1.12
     all
    -1.04
     by
    -1.02
     when
    -1.02
     göre
    -1.00
     find
    -0.96
     any
    -0.96
     those
    -0.95
    POSITIVE LOGITS
     ove
    1.09
     zugel
    1.08
     nunmehr
    1.07
     blauen
    1.05
     bewegen
    1.00
    now
    1.00
     festge
    0.98
    simult
    0.97
     появится
    0.95
     FIVE
    0.94
    Activations Density 0.000%

    No Known Activations