© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33735
    Prev
    Next
    INDEX
    Explanations

    quality of life

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

    The neuron strongly activates on tokens that appear in software‐license and copyright/disclaimer boilerplate 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
    ttps
    -1.05
     sair
    -0.97
     remplace
    -0.93
    tojas
    -0.93
     möchten
    -0.93
    }</
    -0.92
    lijker
    -0.92
    ската
    -0.92
     Eſ
    -0.92
    FontFamily
    -0.90
    POSITIVE LOGITS
     ماش
    0.97
     nella
    0.91
    多少钱
    0.91
     αποτε
    0.86
     erweitert
    0.85
     tocando
    0.84
     도시
    0.84
    museo
    0.84
    始终
    0.84
     trev
    0.83
    Activations Density 0.002%

    No Known Activations