© 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. 11784
    Prev
    Next
    INDEX
    Explanations

    lists of items separated by punctuation

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

    The neuron fires on numeric tokens, particularly multi-digit numbers.

    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
     their
    -1.26
     also
    -1.24
     myös
    -1.16
    不仅
    -1.13
     chứ
    -1.11
    ︵
    -1.06
    他们
    -1.05
     nemlig
    -1.03
     δὲ
    -1.02
     mitte
    -1.02
    POSITIVE LOGITS
     before
    1.50
     rồi
    1.41
     still
    1.39
     who
    1.37
     since
    1.30
     then
    1.27
     vẫn
    1.23
     same
    1.19
     as
    1.17
    before
    1.17
    Activations Density 0.019%

    No Known Activations