© 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. 84345
    Prev
    Next
    INDEX
    Explanations

    configuration =

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

    The neuron detects numeric tokens (integers or decimal numbers).

    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
     دولار
    -0.87
     や
    -0.86
    ViewById
    -0.83
    iacute
    -0.83
     という
    -0.82
    шеб
    -0.82
    kriv
    -0.81
     efter
    -0.80
    ךְ
    -0.79
     drá
    -0.79
    POSITIVE LOGITS
    帖最后由
    0.88
     surrounded
    0.80
     hence
    0.75
     fortunes
    0.74
     these
    0.73
     there
    0.73
     then
    0.70
     unable
    0.70
     therefore
    0.69
     kvä
    0.69
    Activations Density 0.049%

    No Known Activations