© 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. 95722
    Prev
    Next
    INDEX
    Explanations

    public keyword in code

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

    The main thing this neuron does is find numeric literals (numbers and numeric constants) 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
    xa
    -0.86
    quations
    -0.79
     Upper
    -0.79
     فبراير
    -0.79
    ercicio
    -0.79
    专属
    -0.78
    Искәрмәләр
    -0.77
     Helpful
    -0.77
     such
    -0.77
     OTHER
    -0.77
    POSITIVE LOGITS
    ᄌ
    0.94
    ไม่
    0.88
     Renovation
    0.82
    ลอง
    0.81
    Processo
    0.79
    aunque
    0.79
    Więcej
    0.79
    Markets
    0.78
     Thron
    0.78
     thất
    0.77
    Activations Density 0.012%

    No Known Activations