© 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. 10-GEMMASCOPE-RES-131K
    7. 47722
    Prev
    Next
    INDEX
    Explanations

    signing documents or agreements

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

    The neuron detects references to “signing” or “signed” events—that is, when someone signs a law, act, contract, memorandum, petition, etc.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     even
    -2.06
     In
    -2.03
     all
    -2.00
     Some
    -1.98
     really
    -1.79
     of
    -1.76
     >
    -1.73
     Getting
    -1.73
     extravagant
    -1.70
     *
    -1.69
    POSITIVE LOGITS
     zoude
    2.09
     staffel
    2.00
    ︕
    1.98
     pérd
    1.94
     dezelve
    1.79
     niedersachsen
    1.77
    媖
    1.75
     花纹
    1.74
     hunne
    1.74
     incrí
    1.73
    Activations Density 0.030%

    No Known Activations