© 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. 22-GEMMASCOPE-RES-131K
    4. 93403
    Prev
    Next
    INDEX
    Explanations

    numbers and measurements

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

    The neuron responds to numeric and alphanumeric tokens (e.g. standalone numbers, codes, concentrations, years, indices).

    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
    Torna
    -1.01
     after
    -0.96
     fura
    -0.88
    Dá
    -0.86
     coro
    -0.85
     which
    -0.85
     but
    -0.84
    ʐ
    -0.84
     मेरे
    -0.83
     imbal
    -0.82
    POSITIVE LOGITS
     kabát
    0.96
    Appellant
    0.96
    meuble
    0.95
     koncentr
    0.95
     Nationwide
    0.94
     clearColor
    0.93
     několika
    0.93
     uniformes
    0.93
     Euró
    0.91
     specifiche
    0.91
    Activations Density 0.051%

    No Known Activations