© 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. 32997
    Prev
    Next
    INDEX
    Explanations

    API calls and code configurations

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

    The neuron fires on standalone numeric literals (sequences of digits) in code or markup.

    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
     for
    -1.17
     first
    -1.10
     (
    -1.09
     a
    -0.94
     when
    -0.91
     Gre
    -0.91
     word
    -0.86
     although
    -0.86
     call
    -0.85
     Ye
    -0.85
    POSITIVE LOGITS
     srebr
    1.01
     seksi
    0.97
    ionized
    0.94
     اضاف
    0.93
     manag
    0.92
     istr
    0.92
    ceda
    0.91
    次の
    0.91
     Weltkrieg
    0.88
     ਕੀ
    0.88
    Activations Density 0.006%

    No Known Activations