© 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. 10-GEMMASCOPE-RES-131K
    7. 9917
    Prev
    Next
    INDEX
    Explanations

    efforts to improve

    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_10/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
     Uniwers
    -1.55
     zamiast
    -1.51
     those
    -1.45
     for
    -1.45
     proszę
    -1.38
     with
    -1.34
     tych
    -1.30
    Når
    -1.30
    ümüz
    -1.27
     deudas
    -1.26
    POSITIVE LOGITS
     was
    1.23
     вернуть
    1.21
     is
    1.20
     devront
    1.19
     pudieran
    1.18
     lenovo
    1.16
     peuvent
    1.13
     kazak
    1.12
     kawasaki
    1.11
     pourront
    1.10
    Activations Density 0.137%

    No Known Activations