© 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. 34-GEMMASCOPE-RES-131K
    7. 34783
    Prev
    Next
    INDEX
    Explanations

    numbers and descriptive prefixes

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

    The neuron activates strongly on digits, measurements, and other quantitative expressions—that is, it detects numbers and numeric/quantity tokens 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_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
    kese
    -1.34
    Seems
    -1.27
    だいぶ
    -1.25
     acostumb
    -1.24
    ⛥
    -1.21
     clássico
    -1.20
    ogre
    -1.20
    gafas
    -1.19
     takich
    -1.18
    และ
    -1.16
    POSITIVE LOGITS
     although
    1.55
     may
    1.46
     after
    1.38
     Although
    1.37
     during
    1.37
     could
    1.36
     when
    1.31
     might
    1.29
     Though
    1.28
     valuable
    1.27
    Activations Density 0.127%

    No Known Activations