© 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. 124039
    Prev
    Next
    INDEX
    Explanations

    titles, names, or punctuation

    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
    sebagai
    -2.31
     that
    -2.27
    seperti
    -1.98
    secara
    -1.93
     Temperaturen
    -1.91
    isuus
    -1.88
    yaitu
    -1.85
     también
    -1.83
    mereka
    -1.83
    Açık
    -1.82
    POSITIVE LOGITS
     ermittelt
    1.73
    􀂃
    1.45
     کردی
    1.42
     more
    1.38
     festgestellt
    1.38
     BIRTHDAY
    1.36
     commands
    1.33
     umano
    1.32
    几天
    1.30
     كيل
    1.30
    Activations Density 0.090%

    No Known Activations