© 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. 70850
    Prev
    Next
    INDEX
    Explanations

    other languages

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

    This neuron responds to colon punctuation (the “:” character).

    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
     then
    -1.41
     Zuhause
    -1.32
     because
    -1.28
     Gelegenheit
    -1.25
     géographie
    -1.20
     jemanden
    -1.18
     schlechte
    -1.13
     końca
    -1.13
    acamata
    -1.13
     Vergnügen
    -1.10
    POSITIVE LOGITS
     جميع
    1.48
    these
    1.45
     otros
    1.42
     perro
    1.42
     nimmer
    1.39
    อื่น
    1.34
     outros
    1.33
     estos
    1.30
     cán
    1.27
     rendent
    1.26
    Activations Density 0.127%

    No Known Activations