© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 25753
    Prev
    Next
    INDEX
    Explanations

    reporting speech with that

    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_34/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
     you
    -1.30
     which
    -1.17
    它
    -1.00
    Which
    -1.00
    どのように
    -0.99
    的一些
    -0.98
     Our
    -0.98
    Throughput
    -0.95
    woocommerce
    -0.93
    要不然
    -0.93
    POSITIVE LOGITS
     that
    1.55
     though
    1.38
    :
    1.31
     although
    1.28
     further
    1.24
     his
    1.20
    雖然
    1.17
     THOUGH
    1.09
    虽然
    1.07
     FALLS
    1.05
    Activations Density 0.007%

    No Known Activations