© 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. 72106
    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
     at
    -2.08
     on
    -2.05
     for
    -2.05
     create
    -1.80
     through
    -1.76
     requires
    -1.76
     both
    -1.73
     came
    -1.66
     any
    -1.66
     has
    -1.66
    POSITIVE LOGITS
    specifically
    1.75
     REALLY
    1.66
    particularly
    1.63
     goofy
    1.62
     magnific
    1.62
    Directeur
    1.52
     ARISING
    1.52
    might
    1.52
     horrifying
    1.51
     direc
    1.50
    Activations Density 0.000%

    No Known Activations