© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40206
    Prev
    Next
    INDEX
    Explanations

    parentheses and numbers

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

    The neuron flags numeric constants immediately following an open parenthesis, i.e. numbers inside parentheses.

    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
     was
    -2.08
    (,
    -1.78
     với
    -1.78
    bietet
    -1.73
    -*
    -1.72
     nowa
    -1.72
    -!
    -1.71
    ‪.
    -1.69
     trám
    -1.68
    
    -1.68
    POSITIVE LOGITS
     הם
    1.84
    ꜆
    1.76
     They
    1.64
    纮
    1.64
    書いて
    1.59
     have
    1.52
    علق
    1.52
    </strong>
    1.48
    cadeau
    1.48
    Réponse
    1.42
    Activations Density 0.009%

    No Known Activations