© 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. 86700
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions continuing

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

    This neuron activates on closing parentheses in the arithmetic expressions.

    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
     the
    -2.61
    甃
    -1.64
     These
    -1.61
     confira
    -1.60
     ")");
    -1.57
    though
    -1.55
    ﮨ
    -1.55
    проек
    -1.55
    谙
    -1.55
     étoient
    -1.54
    POSITIVE LOGITS
    ↵
    2.00
    ↵↵↵
    1.68
    <bos>
    1.59
          
    1.57
     городской
    1.49
     unbelievable
    1.48
    ↵↵
    1.44
     äußerst
    1.43
     classic
    1.41
     beinahe
    1.40
    Activations Density 0.016%

    No Known Activations