© 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. 10-GEMMASCOPE-RES-131K
    7. 72531
    Prev
    Next
    INDEX
    Explanations

    (b) Background Art / Description

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

    The neuron activates on numeric references that include decimal points (e.g. “(100.5)”, “78.5”, “32 CFR 1901.61”), i.e. section or clause numbers with decimals.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     but
    -3.00
     and
    -2.70
     of
    -2.27
     césped
    -1.94
     podoba
    -1.70
     recentemente
    -1.67
    
    -1.61
     recientemente
    -1.60
     ulica
    -1.59
     redak
    -1.57
    POSITIVE LOGITS
     stället
    2.27
     memerlukan
    1.84
    ⌯
    1.82
    brtc
    1.81
     själ
    1.77
     luminosa
    1.75
     laajenta
    1.73
     cruda
    1.70
    塒
    1.70
     violenta
    1.68
    Activations Density 0.010%

    No Known Activations