© 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. 66510
    Prev
    Next
    INDEX
    Explanations

    other occurrences

    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
     Europese
    -1.03
    ⓪
    -1.02
    château
    -1.02
    <h2>
    -1.01
     namens
    -1.00
     eerste
    -1.00
     italiens
    -0.98
     spektak
    -0.96
    ]?
    -0.96
     guste
    -0.95
    POSITIVE LOGITS
     other
    1.38
     another
    1.16
    そこは
    1.07
     確認
    1.02
     that
    1.02
    Another
    1.00
     シーン
    0.97
    另一方面
    0.94
    それと
    0.91
     동안
    0.91
    Activations Density 0.168%

    No Known Activations