© 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. 34-GEMMASCOPE-RES-131K
    7. 84869
    Prev
    Next
    INDEX
    Explanations

    free software licensing

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

    The neuron strongly activates on boilerplate disclaimers or license/affiliate disclosure lines (e.g. “This library is free software…,” “This post contains affiliate links…,” “It’s How We Got Here” header).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    terima
    -0.82
     スイーツ
    -0.79
     ilgi
    -0.78
     eksp
    -0.78
    shortest
    -0.76
    アドバイス
    -0.76
    ᵇ
    -0.76
    Anyways
    -0.76
     escalier
    -0.74
     this
    -0.74
    POSITIVE LOGITS
     <<"
    0.90
    δι
    0.85
    COE
    0.84
    xtext
    0.83
    TagHelper
    0.77
    瘤
    0.77
     فتح
    0.76
    vations
    0.76
    AndFlush
    0.76
    ведите
    0.75
    Activations Density 0.388%

    No Known Activations