© 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. 34-GEMMASCOPE-RES-131K
    7. 115664
    Prev
    Next
    INDEX
    Explanations

    non-English words and phrases

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

    The neuron activates primarily on multi‐digit numerical tokens.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    _
    -1.23
     D
    -1.16
     l
    -1.15
    er
    -1.13
     Z
    -1.13
     L
    -1.10
    See
    -1.09
     N
    -1.09
     will
    -1.08
     \
    -1.07
    POSITIVE LOGITS
    ESOME
    1.44
    erdings
    1.39
     opportunità
    1.38
     erklär
    1.36
     gäng
    1.34
     erwähnten
    1.34
     citazioni
    1.30
    Кроме
    1.30
     Zustimmung
    1.30
     wesentlichen
    1.29
    Activations Density 0.028%

    No Known Activations