© 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. 10-GEMMASCOPE-RES-131K
    7. 3854
    Prev
    Next
    INDEX
    Explanations

    economic changes and direction

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

    The neuron activates on words and phrases that describe quantitative changes or trends—e.g. rises, falls, records, more than, recovered, broke—around numerical data.

    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
     extrême
    -1.44
    </i>
    -1.30
     the
    -1.29
     his
    -1.27
    ຶ
    -1.17
    Ɩ
    -1.16
     frische
    -1.16
     दौरान
    -1.15
    噢
    -1.15
    才可以
    -1.13
    POSITIVE LOGITS
     churras
    1.55
     regresa
    1.33
    ཨ
    1.31
    言语
    1.29
     Ordem
    1.27
    もありました
    1.24
     Japão
    1.23
     tradução
    1.22
     informou
    1.21
    民众
    1.20
    Activations Density 0.070%

    No Known Activations