© 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. 36445
    Prev
    Next
    INDEX
    Explanations

    comparisons with units

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

    The neuron activates on numerical digits within 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
    #\
    -0.98
     ACCUR
    -0.97
    pport
    -0.95
     Ağ
    -0.95
    celli
    -0.94
     PropTypes
    -0.93
     Arque
    -0.91
    rophi
    -0.90
    ][/
    -0.88
     impac
    -0.88
    POSITIVE LOGITS
     or
    1.54
     anytime
    1.05
     eerste
    0.97
    任何
    0.96
     primeira
    0.93
     anywhere
    0.93
     any
    0.93
     cualquier
    0.92
     valioso
    0.91
     avviene
    0.91
    Activations Density 0.014%

    No Known Activations