© 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. 12780
    Prev
    Next
    INDEX
    Explanations

    sentence endings

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

    This neuron fires on the first substantive token of a new utterance or document segment—i.e. it marks the start of a speaker turn or section.

    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
    vény
    -0.86
     oleju
    -0.85
     dwóch
    -0.81
     треба
    -0.80
    purple
    -0.77
     Bellow
    -0.76
     zweite
    -0.75
    聿
    -0.75
    ='';
    -0.75
    quate
    -0.75
    POSITIVE LOGITS
     menjelaskan
    1.01
     explicó
    0.87
     explicar
    0.82
     explanation
    0.80
    lahoma
    0.79
     vanille
    0.79
     explaining
    0.75
     syk
    0.75
     menambah
    0.75
    ťaž
    0.75
    Activations Density 0.009%

    No Known Activations