© 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. 34-GEMMASCOPE-RES-131K
    7. 98725
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    Because
    -1.14
     продукт
    -0.99
     英語
    -0.99
    Some
    -0.96
     déploy
    -0.95
     plupart
    -0.95
    Keeping
    -0.95
    Since
    -0.93
    システム
    -0.90
    Preface
    -0.90
    POSITIVE LOGITS
    fion
    1.07
    </h2>
    1.04
    苦手
    1.02
    }\]
    0.94
     nocturnal
    0.94
     distress
    0.93
     considered
    0.93
    違和
    0.92
     enveloped
    0.92
     baratos
    0.91
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.