© 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. 33003
    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
     its
    -1.21
     setelah
    -0.93
     esetben
    -0.92
     todella
    -0.92
     lisäksi
    -0.90
     AudioClip
    -0.89
     també
    -0.88
    izoen
    -0.87
     esconde
    -0.86
    之后
    -0.85
    POSITIVE LOGITS
     vying
    0.97
    虽说
    0.96
     rearranging
    0.93
     leftist
    0.89
     आदि
    0.88
    assertNull
    0.88
     bloem
    0.86
    )=>{
    0.85
     расши
    0.84
     derzeit
    0.84
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.