© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 75049
    Prev
    Next
    INDEX
    Explanations

    names starting with common prefixes

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

    This neuron responds to tokens that begin with an uppercase letter—especially those marking the start of section headings or proper-name fragments.

    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
     linken
    -1.59
     kurze
    -1.47
     l
    -1.46
     cause
    -1.40
     the
    -1.40
     overall
    -1.38
     แต่
    -1.34
    支払い
    -1.34
     jeweiligen
    -1.34
     future
    -1.33
    POSITIVE LOGITS
     illustratie
    1.68
     vertrouwen
    1.55
     onderdelen
    1.48
    𓆉
    1.48
     sabid
    1.48
    zło
    1.45
     vervangen
    1.42
     traduit
    1.41
    Là
    1.41
     広場
    1.41
    Activations Density 0.164%

    No Known Activations