© 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. 34-GEMMASCOPE-RES-131K
    7. 66218
    Prev
    Next
    INDEX
    Explanations

    rounding to decimal places

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects rounding‐specification phrases (e.g. “to the nearest ten,” “to four decimal places,” “to 1 dp,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     Belles
    -0.75
    KQ
    -0.74
    outchou
    -0.73
    róż
    -0.72
    Disposable
    -0.71
     Disposable
    -0.71
    dword
    -0.70
    帳
    -0.69
    Fré
    -0.69
    ispo
    -0.69
    POSITIVE LOGITS
     decimal
    4.91
    decimal
    4.00
     decimals
    3.66
    Decimal
    3.58
     Decimal
    3.52
     decim
    3.47
    DECIMAL
    2.95
    dec
    2.92
     Dec
    2.91
    Decimals
    2.80
    Activations Density 0.088%

    No Known Activations