© 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. 10-GEMMASCOPE-RES-131K
    7. 130442
    Prev
    Next
    INDEX
    Explanations

    underscore prefixes

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

    This neuron selectively activates on digit characters (numeric 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_10/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
    -2.45
     Hinsicht
    -2.06
    4
    -1.75
     isolada
    -1.74
     behaup
    -1.67
     seguente
    -1.66
     our
    -1.66
     nuestras
    -1.64
    5
    -1.63
     llorando
    -1.62
    POSITIVE LOGITS
     «
    1.90
     lament
    1.84
     "..\..\
    1.74
    D
    1.73
     –
    1.67
     quoque
    1.66
    ization
    1.64
    煲
    1.64
     将
    1.62
    ものが
    1.59
    Activations Density 0.002%

    No Known Activations