© 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. 34074
    Prev
    Next
    INDEX
    Explanations

    boolean logic; math; code

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

    This neuron activates on numeric tokens, spotting numbers (especially multi‐digit or decimal literals) 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
     before
    -1.27
     on
    -1.02
     new
    -0.98
     „
    -0.96
     re
    -0.94
    .”
    -0.93
     ”
    -0.89
     only
    -0.88
     just
    -0.86
     varias
    -0.86
    POSITIVE LOGITS
     proberen
    1.13
    傒
    1.13
    блок
    1.11
    ܞ
    1.10
     actifs
    1.04
     composés
    1.04
    的食物
    1.03
     betalen
    1.02
     kiezen
    1.02
    ughter
    1.01
    Activations Density 0.047%

    No Known Activations