© 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. 13735
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and code

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

    The neuron flags tokens made up entirely of uppercase letters or digits, i.e. all-caps acronyms/words and numeric values.

    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
     «
    -1.08
     FORCES
    -0.97
    眎
    -0.93
    often
    -0.92
     exceedingly
    -0.90
     isim
    -0.89
    seems
    -0.88
     _
    -0.87
    кових
    -0.87
     
    -0.87
    POSITIVE LOGITS
     Поэтому
    0.88
     ""
    0.87
    훗
    0.84
    aksikan
    0.82
     '';
    0.81
    "।
    0.81
    ()}}
    0.80
    mą
    0.80
    IERRA
    0.79
     after
    0.78
    Activations Density 0.023%

    No Known Activations