© 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. 474
    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
     kimi
    -1.42
     its
    -1.38
     beker
    -1.30
     RESTAUR
    -1.22
    ikti
    -1.14
     kafe
    -1.11
     évé
    -1.09
     abiye
    -1.05
     уже
    -1.04
    ोजना
    -1.03
    POSITIVE LOGITS
    "
    1.09
     führten
    1.06
     angefü
    1.06
    have
    1.02
    Largura
    0.99
     catatan
    0.96
    (,
    0.95
     führte
    0.94
    is
    0.94
    ever
    0.93
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.