© 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. 61130
    Prev
    Next
    INDEX
    Explanations

    scientific notations or abbreviations

    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
    They
    -1.95
    Their
    -1.84
     they
    -1.72
     jų
    -1.48
     They
    -1.48
     acestea
    -1.48
     jejich
    -1.46
    ⻓
    -1.42
     rarely
    -1.42
    they
    -1.42
    POSITIVE LOGITS
     on
    1.61
     вместо
    1.52
     dva
    1.45
     by
    1.45
     via
    1.41
     increíble
    1.34
     primero
    1.31
    ⲣ
    1.31
    ＆
    1.31
     blir
    1.30
    Activations Density 0.218%

    No Known Activations