© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 36464
    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
     カーディガン
    -1.08
    erte
    -1.03
    こんばん
    -1.02
    CompleteListener
    -0.98
    內容簡介
    -0.96
     suspic
    -0.96
    opardi
    -0.96
     exag
    -0.95
     errone
    -0.94
     allusion
    -0.94
    POSITIVE LOGITS
     a
    1.16
     Kartoffeln
    1.13
     an
    1.10
    epam
    0.98
     Gemüse
    0.96
     Tomaten
    0.95
    ля
    0.94
     simple
    0.94
     it
    0.93
    enumi
    0.93
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.