© 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. 13636
    Prev
    Next
    INDEX
    Explanations

    easy to operate

    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
     бампер
    -1.52
     सत्यापित
    -1.35
     чехол
    -1.34
    ִּ
    -1.33
     получают
    -1.31
    meteries
    -1.23
    élément
    -1.23
    οντας
    -1.20
     eğer
    -1.20
    ַּ
    -1.20
    POSITIVE LOGITS
    ׇ
    1.35
    Ẓ
    1.34
     manual
    1.16
    ();*/
    1.16
    detek
    1.13
     الجلد
    1.13
     ἔ
    1.10
    ()));
    1.10
     escondido
    1.10
    操作
    1.09
    Activations Density 0.111%

    No Known Activations