© 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. 73448
    Prev
    Next
    INDEX
    Explanations

    rate of or at

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

    This neuron specializes in spotting multi‐digit numeric tokens—especially figures following “rate” or similar statistical contexts.

    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
    s
    -1.08
    Six
    -1.06
     restless
    -1.02
    Four
    -1.02
    </h2>
    -1.02
    bigsqcup
    -1.02
    <bos>
    -1.01
     grève
    -1.00
    くれて
    -0.99
     breadth
    -0.98
    POSITIVE LOGITS
     Rate
    1.58
    payers
    1.39
     rates
    1.39
     RATE
    1.31
    Rate
    1.20
    ＾＾
    1.18
    蔔
    1.17
    Rates
    1.11
     lage
    1.11
     moderne
    1.09
    Activations Density 0.044%

    No Known Activations