© 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. 65508
    Prev
    Next
    INDEX
    Explanations

    language markup and code snippets

    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
    無法
    -2.33
    玬
    -1.95
     Lengkap
    -1.95
    ﾍ
    -1.95
     nyeri
    -1.93
    ꦢ
    -1.93
     telefonu
    -1.91
    儛
    -1.91
    価格は
    -1.88
     kirim
    -1.86
    POSITIVE LOGITS
     
    2.67
     a
    2.28
    “
    2.17
    -
    2.03
    她就
    1.85
     Perſ
    1.78
     considerada
    1.77
     –
    1.74
    …
    1.73
    ным
    1.66
    Activations Density 0.001%

    No Known Activations