© 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. 34-GEMMASCOPE-RES-131K
    7. 90727
    Prev
    Next
    INDEX
    Explanations

    all quantifier

    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_34/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
    这两个
    -1.73
     in
    -1.38
     einfachen
    -1.36
     with
    -1.34
     menschlichen
    -1.32
     entsprechenden
    -1.30
     gleichen
    -1.30
     väga
    -1.30
     persönliche
    -1.28
     möglichen
    -1.28
    POSITIVE LOGITS
     all
    9.69
     всички
    5.47
     semua
    5.44
     جميع
    5.38
     всех
    5.34
     सभी
    5.22
     wszystkie
    5.16
     всі
    5.13
    所有
    5.03
     모든
    5.00
    Activations Density 0.943%

    No Known Activations