© 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. 41489
    Prev
    Next
    INDEX
    Explanations

    registered officedoicounthmmm

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

    The neuron primarily fires on standalone numeric tokens (digits and numbers) in the text.

    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
     However
    -1.66
     blatantly
    -1.64
    化为
    -1.52
     unrelenting
    -1.50
     Obras
    -1.48
     kwietnia
    -1.47
     two
    -1.45
     undeniably
    -1.43
     grudnia
    -1.41
     sierpnia
    -1.41
    POSITIVE LOGITS
    Hmmm
    1.50
     berücksichtigt
    1.43
     fünf
    1.42
    衹
    1.41
     veränder
    1.34
    蒞
    1.34
    ～、
    1.33
    喲
    1.30
    已經
    1.29
    ’
    1.28
    Activations Density 0.089%

    No Known Activations