© 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. 10-GEMMASCOPE-RES-131K
    7. 105463
    Prev
    Next
    INDEX
    Explanations

    blog post awards

    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_10/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
     again
    -1.37
     resistente
    -1.36
    ”,
    -1.33
    hynch
    -1.31
    )',
    -1.29
    οιν
    -1.28
    🩹
    -1.24
     sép
    -1.23
     teknis
    -1.23
     besö
    -1.23
    POSITIVE LOGITS
     this
    1.55
     other
    1.38
    灩
    1.26
     others
    1.25
     it
    1.21
     doing
    1.18
     Aussehen
    1.18
     more
    1.17
    Kalau
    1.16
    這個
    1.15
    Activations Density 0.061%

    No Known Activations