© 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. 853
    Prev
    Next
    INDEX
    Explanations

    three-point shots and scoring

    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
     Algunos
    -1.41
    ﻒ
    -1.41
    ल्ड
    -1.39
     Estos
    -1.38
     thoſe
    -1.38
     rigue
    -1.37
     eléctricas
    -1.35
     EXAMPLE
    -1.34
    ซึ่ง
    -1.32
     التي
    -1.30
    POSITIVE LOGITS
     as
    2.30
     similar
    1.58
     the
    1.56
     more
    1.47
     very
    1.46
    s
    1.44
    es
    1.42
    uegos
    1.41
     two
    1.38
     tačiau
    1.38
    Activations Density 0.008%

    No Known Activations