© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13161
    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
     algu
    -1.15
     می‌گو
    -1.14
    şam
    -1.13
     about
    -1.07
     primas
    -1.05
    PyTuple
    -1.05
    closedir
    -1.05
    aktionen
    -1.05
    wär
    -1.05
    Cuánt
    -1.05
    POSITIVE LOGITS
     ailing
    1.34
    1.16
    .
    1.15
    1.15
    1.14
    詐
    1.13
    1.12
     dieselben
    1.11
     различ
    1.11
    qu
    1.11
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.