© 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. 105286
    Prev
    Next
    INDEX
    Explanations

    symbols followed by 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
     two
    -2.52
    Surprisingly
    -2.34
     burgeoning
    -2.28
     FOR
    -2.25
     unrelenting
    -2.17
     Generally
    -2.16
     Surprisingly
    -2.14
     four
    -2.13
     When
    -2.09
     Sometimes
    -2.09
    POSITIVE LOGITS
     Dinas
    2.48
     monstrous
    2.36
     ridiculously
    2.34
    粜
    2.31
    iffance
    2.31
     wondrous
    2.30
    苤
    2.30
    🧌
    2.27
     dismal
    2.25
     delightfully
    2.23
    Activations Density 0.001%

    No Known Activations