© 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. 119877
    Prev
    Next
    INDEX
    Explanations

    foreign scripts

    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
     смог
    -2.36
    嵙
    -2.33
     但
    -2.23
    ۸
    -2.22
    她
    -2.11
    ጄ
    -2.11
    癀
    -2.06
     preguntó
    -2.06
     zosta
    -2.05
    ┙
    -2.02
    POSITIVE LOGITS
    ’
    2.52
    and
    2.17
    Z
    2.08
     “
    2.06
    ’’
    2.05
    ‘‘
    2.03
    m
    2.02
    ?
    1.95
    ,”
    1.93
    ↵
    1.92
    Activations Density 0.006%

    No Known Activations