© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 84588
    Prev
    Next
    INDEX
    Explanations

    mathematics and geometry

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

    This neuron detects tokens containing digits (e.g. numeric strings and URL/ID segments).

    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
     saldo
    -0.75
    retVal
    -0.72
     виро
    -0.71
     états
    -0.71
    }$_
    -0.69
     directly
    -0.68
    ײ
    -0.68
     rosario
    -0.68
    Tutorial
    -0.67
     godzin
    -0.67
    POSITIVE LOGITS
     mathematicians
    1.21
     mathematician
    1.09
     доказа
    1.01
     гео
    0.98
     математи
    0.96
     Mathematics
    0.93
     cohomology
    0.93
     Math
    0.92
     prove
    0.91
     Maths
    0.91
    Activations Density 0.003%

    No Known Activations