© 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. 39436
    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
     pintor
    -1.36
     chrétien
    -1.23
    futbolista
    -1.19
     Новости
    -1.15
    monies
    -1.14
     filós
    -1.13
    头像
    -1.12
    faker
    -1.11
    ciem
    -1.11
     conseiller
    -1.10
    POSITIVE LOGITS
     avendo
    1.19
     発
    1.08
     パー
    1.06
    secret
    1.05
    如果你
    1.02
     Stateless
    1.00
     الحكومة
    0.99
     있다
    0.98
    カメラ
    0.98
    在我们
    0.98
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.