© 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. 67506
    Prev
    Next
    INDEX
    Explanations

    sentence ending

    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
    Ẹ
    -1.14
    pptx
    -1.11
     різних
    -1.09
    ޏ
    -1.09
    ejemplo
    -1.07
     például
    -1.07
    ̈
    -1.05
    जब
    -1.05
    signo
    -1.05
     geladeira
    -1.04
    POSITIVE LOGITS
    ポイントは
    1.45
    価格は
    1.37
     contact
    1.23
     stay
    1.18
     visit
    1.18
    новременно
    1.17
    www
    1.13
    푇
    1.09
     located
    1.06
     join
    1.05
    Activations Density 0.013%

    No Known Activations