© 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. 101693
    Prev
    Next
    INDEX
    Explanations

    Baba Alibaba ABA

    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
    '
    -3.23
    .”
    -2.78
    ).
    -2.75
    呖
    -2.73
    はその
    -2.73
    僻
    -2.64
    哺
    -2.61
     is
    -2.55
     regiões
    -2.50
    蝰
    -2.45
    POSITIVE LOGITS
    {
    3.19
     Hundreds
    2.80
    今月
    2.47
    During
    2.42
     kenyataan
    2.42
    Since
    2.41
    日本で
    2.38
    Because
    2.36
     Primarily
    2.36
    After
    2.34
    Activations Density 0.002%

    No Known Activations