© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101371
    Prev
    Next
    INDEX
    Explanations

    Roman numeral sections

    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
     other
    -1.73
     "
    -1.59
     the
    -1.59
     Other
    -1.51
     altres
    -1.44
    {
    -1.32
     “
    -1.30
     latter
    -1.28
     outras
    -1.19
     andere
    -1.17
    POSITIVE LOGITS
    tiert
    1.58
     Sebuah
    1.44
     Lø
    1.40
    ہرست
    1.40
    дёт
    1.33
    ṇa
    1.28
    Подготовка
    1.27
    ⢱
    1.27
    ETING
    1.27
     sejak
    1.27
    Activations Density 0.216%

    No Known Activations