© 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. 63927
    Prev
    Next
    INDEX
    Explanations

    rounding to decimal places

    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
    mergeFrom
    -0.94
    ají
    -0.82
    sendRedirect
    -0.79
    contentValues
    -0.78
     מי
    -0.78
    BorderSize
    -0.77
    愎
    -0.77
     desconocido
    -0.76
     Solomon
    -0.76
    thenReturn
    -0.76
    POSITIVE LOGITS
     rounded
    4.94
     rounding
    4.28
    rounded
    4.19
     round
    3.81
     Round
    3.56
    Rounded
    3.55
    Rounding
    3.44
     Rounded
    3.39
    round
    3.38
    Round
    3.27
    Activations Density 0.111%

    No Known Activations