© 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. 105584
    Prev
    Next
    INDEX
    Explanations

    python code fragments

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

    The neuron fires on numeric literal tokens in code, especially floating-point 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_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
     الشرطة
    -1.66
     addirittura
    -1.51
    谥
    -1.49
    rarr
    -1.48
     parlando
    -1.45
    謚
    -1.43
     bisog
    -1.41
    笈
    -1.39
     obiettivi
    -1.38
    columnwidth
    -1.36
    POSITIVE LOGITS
     we
    2.16
     the
    2.08
     our
    2.03
    我们
    1.86
     from
    1.56
    我們
    1.56
     které
    1.50
    när
    1.47
     liefern
    1.43
    欤
    1.42
    Activations Density 0.012%

    No Known Activations