© 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. 84248
    Prev
    Next
    INDEX
    Explanations

    related to legal proceedings and claims

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

    The neuron responds to formal technical or patent-style prose (e.g. specification sections, detailed descriptions, numbered examples) rather than ordinary narrative or journalistic 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_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
     basé
    -1.13
     قوان
    -1.05
     tiež
    -1.02
     underage
    -0.98
     أيضًا
    -0.97
     Afterward
    -0.96
     laborers
    -0.93
    Ethylbenzene
    -0.93
     wilfully
    -0.93
     дописа
    -0.92
    POSITIVE LOGITS
    yled
    0.93
     by
    0.90
    czyna
    0.88
     plainly
    0.88
    queles
    0.85
     diverso
    0.85
     utara
    0.84
     ry
    0.83
     matters
    0.83
    ಡ
    0.83
    Activations Density 0.009%

    No Known Activations