© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30579
    Prev
    Next
    INDEX
    Explanations

    quantities in billions

    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
     Million
    -0.91
     مليون
    -0.84
    Million
    -0.81
    До
    -0.79
    Detective
    -0.78
    百万
    -0.77
    NSYLVANIA
    -0.77
     MILLION
    -0.72
    Mill
    -0.72
     Detective
    -0.71
    POSITIVE LOGITS
     billions
    2.11
     billion
    1.41
    Billi
    1.25
    billi
    1.14
     tens
    1.07
    billion
    1.05
     Billi
    1.05
    tens
    1.02
    Tens
    1.02
     dizaines
    0.97
    Activations Density 0.041%

    No Known Activations