© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26207
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

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

    The neuron picks up numerical literal tokens (e.g. integers or decimals) wherever they occur 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
     or
    -0.84
    нную
    -0.84
     only
    -0.84
     MPs
    -0.80
    หน่อย
    -0.78
     العديد
    -0.77
     at
    -0.76
    horabuena
    -0.76
     владе
    -0.75
     k
    -0.73
    POSITIVE LOGITS
     ɛ
    0.99
    still
    0.98
     POU
    0.95
     スクール
    0.95
    特朗
    0.94
    acidade
    0.90
     frontend
    0.90
     possibilità
    0.88
    хівовано
    0.88
     MOUSE
    0.87
    Activations Density 0.006%

    No Known Activations