© 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. 68594
    Prev
    Next
    INDEX
    Explanations

    code with urls and variables

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

    The neuron activates on standalone numeric tokens (number literals) in code or 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
     PICT
    -0.94
     LECT
    -0.84
    Ŷ
    -0.80
     romp
    -0.80
    ŷ
    -0.77
    PostMapping
    -0.77
    giphy
    -0.76
     asin
    -0.75
     carcin
    -0.74
     biofilm
    -0.74
    POSITIVE LOGITS
    Glej
    0.89
     efekty
    0.88
    Ÿ
    0.87
    IVOS
    0.84
    //'
    0.81
    raquo
    0.81
     ekolog
    0.81
    Kilde
    0.80
    ndon
    0.80
     ocupado
    0.79
    Activations Density 0.006%

    No Known Activations