© 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. 13694
    Prev
    Next
    INDEX
    Explanations

    measurements and specifications

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

    The neuron is detecting numeric tokens—specifically standalone numbers and measurements 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_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
    Много
    -1.13
     popoli
    -0.99
    omaly
    -0.98
    Several
    -0.98
    leyin
    -0.92
    lebens
    -0.92
     ложка
    -0.90
     そう
    -0.90
    Many
    -0.87
     принад
    -0.87
    POSITIVE LOGITS
     size
    1.39
     $
    1.10
     extrapolated
    1.03
    ⅰ
    1.03
    ⊂
    1.00
    peech
    0.99
     mobilized
    0.98
     about
    0.96
    क़
    0.96
    NOWLEDGE
    0.95
    Activations Density 0.010%

    No Known Activations