© 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. 21255
    Prev
    Next
    INDEX
    Explanations

    currency and prices

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

    The neuron fires on decimal points (and the digits immediately after) in numerical values such as prices or measurements.

    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
     kvalitet
    -1.79
     signifie
    -1.71
     besonder
    -1.70
     biblia
    -1.70
     trafik
    -1.63
     nativo
    -1.63
     🤩
    -1.63
    eeeee
    -1.60
     meur
    -1.59
     godk
    -1.59
    POSITIVE LOGITS
     or
    2.38
     and
    1.99
     from
    1.85
    してきました
    1.57
     including
    1.51
    していました
    1.51
    <bos>
    1.47
     less
    1.44
    $,
    1.43
    绉
    1.42
    Activations Density 0.017%

    No Known Activations