© 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. 65214
    Prev
    Next
    INDEX
    Explanations

    sentence ending punctuation

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

    The neuron flags long, multi‐syllable content words (especially complex nouns).

    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
    zbęd
    -1.48
     ceux
    -1.44
    包括
    -1.42
     Atención
    -1.35
     misschien
    -1.34
    最初
    -1.33
     Boletín
    -1.33
    那些
    -1.33
     nuest
    -1.32
     vendeurs
    -1.31
    POSITIVE LOGITS
     this
    1.87
     to
    1.56
     办
    1.27
    CUSSION
    1.26
     T
    1.26
     pensó
    1.24
     The
    1.23
     '*':
    1.22
     It
    1.22
     $
    1.22
    Activations Density 0.106%

    No Known Activations