© 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. 1624
    Prev
    Next
    INDEX
    Explanations

    ban on

    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
     have
    -2.36
    した
    -2.31
     \
    -2.25
     //
    -2.23
     Superan
    -2.09
    싶
    -2.02
     mám
    -1.98
    点的
    -1.97
    葙
    -1.93
    とはいえ
    -1.88
    POSITIVE LOGITS
     высоким
    2.23
    oren
    2.20
    rophes
    2.17
     récomp
    2.14
     dekoratif
    2.09
     بهترین
    2.06
    TERY
    2.05
    ofthe
    2.02
    夤
    2.00
    have
    1.98
    Activations Density 0.005%

    No Known Activations