© 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. 22-GEMMASCOPE-RES-131K
    7. 69048
    Prev
    Next
    INDEX
    Explanations

    numerical ratings and checks

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

    The neuron is attuned to quantitative and measurement‐related language—especially numbers (digits) and adjoining technical terms that appear in data, metrics, or experimental 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_22/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
     chré
    -1.84
     religieuses
    -1.62
     about
    -1.38
     chrétiens
    -1.35
    2
    -1.33
     friends
    -1.31
     ways
    -1.30
     работников
    -1.30
     ideas
    -1.29
     kinds
    -1.29
    POSITIVE LOGITS
    ַּ
    1.70
    ּוֹ
    1.47
     مباراة
    1.45
     torsdag
    1.41
    ֶּ
    1.38
    ೦
    1.37
    Vastaa
    1.34
     fredag
    1.31
    ִּ
    1.30
     campeonato
    1.30
    Activations Density 0.001%

    No Known Activations