© 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. 71455
    Prev
    Next
    INDEX
    Explanations

    route definitions and requests

    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
     any
    -1.34
     from
    -1.33
     in
    -1.33
     to
    -1.16
    峻
    -1.14
     réus
    -1.13
     other
    -1.09
     such
    -1.07
     empezaron
    -1.07
     bolsos
    -1.05
    POSITIVE LOGITS
    取决
    1.10
    大丈夫です
    1.10
     zult
    1.02
    这也是
    1.02
     momentous
    1.02
    ępu
    1.01
    並沒有
    1.00
     perdón
    0.99
    有一個
    0.98
    來看
    0.98
    Activations Density 0.001%

    No Known Activations