© 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. 22-GEMMASCOPE-RES-131K
    7. 72948
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with exponents

    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_22/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
    rrr
    -1.05
     Because
    -1.00
    rrrr
    -1.00
     only
    -0.99
     damaligen
    -0.98
    🎛
    -0.96
     =
    -0.95
     didukung
    -0.93
    -/**
    -0.92
    具体的な
    -0.89
    POSITIVE LOGITS
    ֯
    1.23
     you
    1.18
    ciri
    1.03
    atangan
    1.03
    WebMethod
    1.03
     صفحات
    1.02
     Seconds
    0.99
    vateľ
    0.98
    tuan
    0.98
    íram
    0.98
    Activations Density 0.012%

    No Known Activations