© 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. 72814
    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
     their
    -1.16
     when
    -1.03
     THE
    -0.95
    GRAFÍA
    -0.94
     will
    -0.94
     of
    -0.93
     after
    -0.90
     (~
    -0.90
     achieve
    -0.90
     get
    -0.88
    POSITIVE LOGITS
    Enfer
    1.07
     різних
    1.05
    ままで
    1.04
     maniere
    1.02
     Rises
    1.01
    不仅仅
    1.00
     آباد
    1.00
    oped
    0.96
     VizieR
    0.95
     again
    0.95
    Activations Density 0.000%

    No Known Activations