© 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. 39910
    Prev
    Next
    INDEX
    Explanations

    multi-language code snippets

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

    The neuron primarily detects numeric literals (tokens consisting of digits) 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
     it
    -0.94
    utiny
    -0.91
     IX
    -0.90
     zufolge
    -0.86
     MO
    -0.86
    нера
    -0.85
    JsonObject
    -0.85
     produt
    -0.85
     GOP
    -0.85
    啻
    -0.84
    POSITIVE LOGITS
    わたしは
    1.09
    私たちは
    1.09
     différentes
    1.05
    夏休み
    1.03
    さあ
    1.01
    色んな
    1.00
     verschillende
    0.98
    这篇
    0.97
    最近は
    0.96
    cleos
    0.96
    Activations Density 0.022%

    No Known Activations