© 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. 98256
    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
     even
    -1.36
    hdysval
    -1.31
     or
    -1.27
     for
    -1.24
     not
    -1.19
     any
    -1.16
     lalu
    -1.13
    子さん
    -1.13
     their
    -1.13
     this
    -1.13
    POSITIVE LOGITS
     brachten
    1.23
     œufs
    1.21
    Voltar
    1.20
    Imagens
    1.19
    instead
    1.16
    Tils
    1.15
    kinda
    1.15
    creates
    1.14
     ameste
    1.14
     küche
    1.13
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.