© 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. 70879
    Prev
    Next
    INDEX
    Explanations

    only authorized or official

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

    The neuron activates on numeric tokens, i.e. it detects numbers (quantities, measurements, IDs) 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
    Thanos
    -1.00
    isantes
    -0.96
    ninger
    -0.95
    も多い
    -0.94
     einfach
    -0.93
     мамы
    -0.93
    enziali
    -0.92
    が多い
    -0.91
    ycznych
    -0.87
    多い
    -0.86
    POSITIVE LOGITS
     authorized
    1.79
     approved
    1.62
     only
    1.56
     legitimate
    1.51
     properly
    1.45
     official
    1.43
     authorised
    1.42
     proper
    1.38
     ONLY
    1.30
     только
    1.27
    Activations Density 0.071%

    No Known Activations