© 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. 129134
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric literals (sequences of digits) in the code.

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

    Scanner object instantiation

    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
    estia
    -1.12
     бампер
    -1.07
     với
    -1.06
    成为
    -1.05
     чехол
    -1.02
     tanpa
    -1.02
    olarmente
    -1.02
     eerste
    -1.01
     yardım
    -1.01
    ourage
    -0.98
    POSITIVE LOGITS
    fő
    1.23
     of
    1.16
    cursions
    1.08
     بيها
    1.04
    ();
    1.04
     ему
    1.02
     opportunities
    0.99
     nór
    0.98
     ガード
    0.98
    habited
    0.97
    Activations Density 0.000%

    No Known Activations