© 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. 118250
    Prev
    Next
    INDEX
    Explanations

    number fixed to decimal places

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

    The neuron fires on numeric values and number-related operations in code (e.g., literals like 0, 1, 7 and functions such as Number, toFixed).

    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
     SER
    -0.75
     Técnico
    -0.73
    從
    -0.72
     silent
    -0.72
    ⃟
    -0.70
    quiet
    -0.69
    çar
    -0.69
     franquicia
    -0.69
    jalá
    -0.68
     Grafik
    -0.68
    POSITIVE LOGITS
    toFixed
    2.09
     fixed
    1.98
    fixed
    1.49
    Fixed
    1.48
     Fixed
    1.43
     fixes
    1.23
    FIXED
    1.21
    固定
    1.14
     fixation
    1.08
     fix
    1.06
    Activations Density 0.010%

    No Known Activations