© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27046
    Prev
    Next
    INDEX
    Explanations

    how things are done or presented

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    埌
    -1.13
     myös
    -1.12
    ныя
    -1.08
    ってお
    -1.04
     intégré
    -1.03
    レンダー
    -1.02
     entrando
    -1.00
     tranquil
    -0.99
     nacidos
    -0.99
    (___
    -0.99
    POSITIVE LOGITS
     attempt
    1.38
     barely
    1.25
     attempts
    1.21
     attempting
    1.18
     rique
    1.16
     only
    1.13
    attempt
    1.13
     over
    1.12
     an
    1.08
     poorly
    1.08
    Activations Density 0.093%

    No Known Activations