© 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. 67757
    Prev
    Next
    INDEX
    Explanations

    independent verification and proof

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

    The neuron activates on the formal, boilerplate phrases and terms used in financial or commercial advertisements (e.g. “For Lease and Purchase,” “100% protected,” “(We moves first)”).

    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
     stále
    -1.02
    ,
    -0.97
    minated
    -0.88
    чайно
    -0.86
     informace
    -0.86
    сва
    -0.83
     pomá
    -0.83
     muñeca
    -0.83
    Congratulations
    -0.83
     informací
    -0.83
    POSITIVE LOGITS
     transparent
    1.20
     prove
    1.19
     verification
    1.16
     transparency
    1.16
     independently
    1.14
     verified
    1.13
     agreed
    1.10
     proof
    1.05
     independent
    1.02
     unbiased
    1.01
    Activations Density 0.040%

    No Known Activations