© 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. 39765
    Prev
    Next
    INDEX
    Explanations

    MEMORANDUM or ORDER

    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
     all
    -1.17
     וכן
    -1.16
     latter
    -1.16
     other
    -1.15
    ↵↵
    -1.15
     its
    -1.14
    lorin
    -1.07
     last
    -1.02
     berbagai
    -1.01
     подготовка
    -1.01
    POSITIVE LOGITS
    شكرا
    1.13
    »).
    1.13
     entré
    1.09
     ég
    1.09
    というわけで
    1.05
     пишет
    1.05
    疍
    1.05
    nitus
    1.03
    Öffnungszeiten
    1.03
    पर
    1.01
    Activations Density 0.006%

    No Known Activations