© 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. 129188
    Prev
    Next
    INDEX
    Explanations

    The neuron responds to numeric literals (sequences of digits) in code or text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    code syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    automne
    -0.96
    #--
    -0.95
     Also
    -0.94
     Ruß
    -0.92
    Also
    -0.90
     berbasis
    -0.90
     So
    -0.90
     anche
    -0.89
    farol
    -0.85
     Let
    -0.85
    POSITIVE LOGITS
    änderung
    1.00
     neemt
    0.99
    itrile
    0.97
    尙
    0.95
     GUARANTE
    0.94
    ckte
    0.92
    역
    0.90
     ราคา
    0.90
    เห็น
    0.88
     atan
    0.86
    Activations Density 0.002%

    No Known Activations