© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 57419
    Prev
    Next
    INDEX
    Explanations

    legal and contractual contexts

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

    The neuron flags boilerplate patent/legal style language—i.e. the formal technical‐specification and “prior art” phrasing common in patent documents.

    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
    ➢
    -0.81
     lacoste
    -0.81
     valido
    -0.78
    Esperamos
    -0.77
    ✻
    -0.75
    Métodos
    -0.74
     論
    -0.74
     valentino
    -0.73
    是非
    -0.73
     studied
    -0.73
    POSITIVE LOGITS
     (§
    1.31
     BGB
    1.06
     §§
    1.01
     §
    0.98
     частей
    0.92
     leistungs
    0.90
     cromado
    0.90
     cauza
    0.89
    artz
    0.88
     дорог
    0.87
    Activations Density 0.052%

    No Known Activations