© 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. 118934
    Prev
    Next
    INDEX
    Explanations

    edu related words

    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
     takže
    -2.45
     включая
    -2.42
    。】
    -2.34
    鞮
    -2.25
    '
    -2.19
    ashqai
    -2.17
    Aiheesta
    -2.14
    籴
    -2.09
     ибо
    -2.09
     unión
    -2.05
    POSITIVE LOGITS
    {
    2.47
    1
    2.22
     fashioned
    2.20
    *
    2.20
    The
    2.20
    ’
    2.19
    而在
    2.17
    鱟
    2.17
    7
    2.17
    都在
    2.14
    Activations Density 0.004%

    No Known Activations