© 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. 69243
    Prev
    Next
    INDEX
    Explanations

    Congress transport

    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
     ``
    -1.32
     medan
    -1.17
     разнообраз
    -1.16
     menant
    -1.14
     («
    -1.14
     muka
    -1.13
     concreta
    -1.12
     dava
    -1.10
     ¨
    -1.09
     mondi
    -1.09
    POSITIVE LOGITS
     spesso
    1.16
    ↵
    1.07
     notwendi
    1.05
     at
    1.05
    ؔ
    1.02
     vendedor
    0.99
    哋
    0.98
    irsi
    0.98
     transportasi
    0.96
    </h2>
    0.96
    Activations Density 0.116%

    No Known Activations