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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67498
    Prev
    Next
    INDEX
    Explanations

    code assignments and continuations

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

    The neuron is detecting numeric literal tokens (e.g. integers or decimal values) in code and 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
    peut
    -1.05
    beu
    -1.05
    joueurs
    -1.02
    foque
    -0.97
    très
    -0.96
     konkrét
    -0.96
     karna
    -0.95
     ägg
    -0.95
    ához
    -0.95
    freies
    -0.95
    POSITIVE LOGITS
     another
    1.08
     continues
    1.06
    ضل
    1.00
     less
    0.99
     gradually
    0.97
     continued
    0.97
     continuing
    0.95
    쾌
    0.93
     continue
    0.93
    At
    0.93
    Activations Density 0.003%

    No Known Activations