© 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. 130438
    Prev
    Next
    INDEX
    Explanations

    Japanese possessives and code calls

    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
    m
    -2.61
    涐
    -2.39
     ustal
    -2.38
    ѣмъ
    -2.30
    grandchildren
    -2.28
    𝐃
    -2.25
     '='
    -2.17
    猡
    -2.14
    इटम
    -2.14
    which
    -2.14
    POSITIVE LOGITS
     foray
    2.64
     Пі
    2.53
     stren
    2.30
     Officially
    2.28
     acheté
    2.23
    𖣘
    2.22
     résulte
    2.20
     he
    2.19
    2
    2.19
     Ее
    2.17
    Activations Density 0.001%

    No Known Activations