© 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. 22-GEMMASCOPE-RES-131K
    7. 27483
    Prev
    Next
    INDEX
    Explanations

    code symbols and structure

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

    The main thing this neuron does is find numeric literals (including integers and floats) 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
    彼らは
    -0.96
    composed
    -0.94
    +='
    -0.93
    possessed
    -0.93
    Texte
    -0.93
     their
    -0.93
     داشتند
    -0.92
     يساعد
    -0.92
    Thêm
    -0.90
    ]='
    -0.89
    POSITIVE LOGITS
    wordpress
    0.82
    onActivityResult
    0.81
     then
    0.80
    붉
    0.78
     Inorg
    0.78
    仍
    0.78
     wouldn
    0.77
     affari
    0.77
    aringan
    0.75
    か月
    0.75
    Activations Density 0.002%

    No Known Activations