© 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. 22-GEMMASCOPE-RES-131K
    7. 54423
    Prev
    Next
    INDEX
    Explanations

    file headers and copyright notices

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

    The neuron selectively fires on number tokens (numeric literals) 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_22/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
     sosis
    -1.52
     sekunder
    -1.48
     tinta
    -1.41
    ledes
    -1.40
    риса
    -1.38
    ''');
    -1.37
     conster
    -1.37
     不能
    -1.34
     diren
    -1.34
     manuten
    -1.34
    POSITIVE LOGITS
     and
    2.42
     zoveel
    1.23
    .
    1.23
     iedere
    1.22
    _
    1.15
    タクシー
    1.10
     necesitamos
    1.09
     ПОД
    1.06
     zowel
    1.05
     regelmatig
    1.05
    Activations Density 0.005%

    No Known Activations