© 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. 47950
    Prev
    Next
    INDEX
    Explanations

    moody, mottled, names

    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
     заметил
    -2.83
    镚
    -2.80
     fostered
    -2.58
     Даже
    -2.56
     Nowadays
    -2.50
     Есть
    -2.50
     Things
    -2.47
    有一定的
    -2.47
     Practically
    -2.45
     Officially
    -2.45
    POSITIVE LOGITS
    婞
    3.19
    i
    3.09
    .
    3.00
    the
    2.89
     =
    2.61
    栳
    2.59
    {
    2.47
    蚡
    2.47
    ي
    2.30
    ”？
    2.27
    Activations Density 0.003%

    No Known Activations