© 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. 34-GEMMASCOPE-RES-131K
    7. 746
    Prev
    Next
    INDEX
    Explanations

    requirements, code, options

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

    The neuron primarily detects numeric tokens (digits and number 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_34/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
    需求
    -1.34
    需要
    -1.27
     requirements
    -1.27
    isRequired
    -1.26
     needed
    -1.22
     requirement
    -1.19
     cần
    -1.16
    IsRequired
    -1.16
     necessities
    -1.13
     needs
    -1.13
    POSITIVE LOGITS
    tund
    0.80
     ____________
    0.80
     pn
    0.79
     plazos
    0.79
    must
    0.79
    difficult
    0.78
    basti
    0.78
     impossível
    0.78
    MSG
    0.78
    provided
    0.77
    Activations Density 0.009%

    No Known Activations